ICML 2022 Events with Videos
Affinity Events
Awards
Award Ceremony & Closing Remarks
Blue Sky Ideas
- Overcoming Adversarial Attacks for Human-in-the-Loop Applications
- Ad Hoc Teamwork in the Presence of Adversaries
- Learner Knowledge Levels in Adversarial Machine Learning
- Easy Batch Normalization
- Adversarial Training Improve Joint Energy-Based Generative Modelling
- Multi-step domain adaptation by adversarial attack to $\mathcal{H} \Delta \mathcal{H}$-divergence
Breaks
Breakouts + Discussions
Cancelleds
Closings
Closing Remarks
Closing messages
Closing remarks
Closing remarks
Contributed Live Talks
- Human-AI Collaboration in Decision-Making: Beyond Learning to Defer. Diogo Leitao
- Machine Explanations and Human Understanding. Chacha Chen
- Human-machine collaboration for reusable and scalable models of remote sensing imagery analysis. Lexie Yang
- How to Talk so Robots will Learn: Instructions, Descriptions, Alignment. Ted Sumers
Contributed Recorded Talks
Contributed Talks
- Efficient Continuous Spatio-Temporal Simulation with Graph Spline Networks, Chuanbo Hua
- Learning to solve PDE constraint inverse problem using Graph Network, Qingqing Zhao
- Understanding the evolution of tumours using hybrid deep generative models, Tom Ouellette
- A Density Functional Recommendation Approach for Accurate Predictions of Vertical Spin Splitting of Transition Metal Complexes, Chenru Duan
- Generative power of a protein language model trained on multiple sequence alignments
- BayesTME: A reference-free Bayesian method for end-to-end analysis of spatial transcriptomic data
- SPACE-GM: geometric deep learning of disease-associated microenvironments from multiplex spatial protein profiles.
Contributed Talks
Contributed talks
- DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis with Autoencoding Generative Adversarial Networks
- Generating Detailed Music Datasets with Neural Audio Synthesis
- Adversarial Audio Synthesis with Complex-valued Polynomial Networks
- Speech De-warping: Unsupervised Pre-training for Data-Efficient Text-to-Speech on Low Resource Languages
- DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
- Continuous-time event-based GRU for activity-sparse inference and learning
- Irregularly-Sampled Time Series Modeling with Spline Networks
- Individually Fair Learning with One-Sided Feedback
- Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence toMirror Descent
- Reward Reports for Reinforcement Learning
- Heat Diffusion Based Recurrent Neural Differential Equations
- On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
- Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
- A Game-Theoretic Perspective on Trust in Recommendation
DataPerf Talks
Discussions
Discussion Panels
- Panel Discussion with Morning Speakers
- Dynamic neural networks: Present and Future
- Panel
- Panel Discussion with Afternoon Speakers
- Machine Learning for Scientific Discovery
- Discussion. Deploying Human-Machine Teams in Practice (Ernest and Wendy)
- Panel
- Panel/Discussion. Human-Machine Teams for Mathematicians (Igor, Tony, Talia, and Petar)
- Panel
Discussion Panel; In-person ands on zoom
Expo Demonstrations
- AEPsych: active learning for human perception and preferences
- TorchRL: the PyTorch RL Domain library
- Creating a scalable, reproducible, and reliable environment for model development with AstraZeneca and W&B.
- Enabling Hand Gesture Customization on Wrist-Worn Devices
- Robust and Fast Detection of Toxic Speech Content via Machine Learning
Expo Talks
- Enabling Hand Gesture Customization on Wrist-Worn Devices
- Anatomy of Vowpal Wabbit. Reductions cookbook
- Challenges with Graph Neural Networks
- GraphWorld: Fake Graphs Bring Real Insights for GNNs
- Discrete optimization with GNNs
- What is new in Vowpal Wabbit 9
- Robust GNNs
- TF-GNN: Graph Neural Networks Inside TensorFlow
- Azure Personalizer Service (VW-as-a-service)
- New Challenges in Graph Mining: Scalability, Stability, and Privacy Applications
- Advances in Graph Learning and Building
- Advances in Parallel Clustering
- Advances in Private Algorithms: Clustering and Graph Mining
- A simple introduction to TF-GNN models
- Algorithmic Benchmarking with GBBS
- Benchmarking GNNs with GraphWorld
- Closing Remarks
Expo Talk Panels
- Challenges Of Applying Graph Neural Networks
- Enabling Hand Gesture Customization on Wrist-Worn Devices
- Knowledge graph-based recommendation framework identifies drivers of resistance in EGFR mutant non-small cell lung cancer
- Machine learning for drug discovery: Challenges and opportunities
- Towards Robust Waveform-Based Acoustic Models
Expo Workshops
Expo talks
In-person talks
Introductions
Introduction and Opening Remarks
Invited Breaks
Invited Keynote Presentations
Invited Speakers
- Learning from Preference Feedback in Combinatorial Action Spaces
- Or Zamir: Planting undetectable backdoors in Machine Learning models
- Delayed Feedback in Generalised Linear Bandits Revisited
- Aaron Roth: An Algorithmic Framework for Bias Bounties
- Beyond Learning from Demonstrations
- Chelsea Finn: Adapting Deep Networks to Distribution Shift with Minimal Assumptions
- Decentralized Learning in Online Queuing Systems
- Nicolas Papernot: What does it mean to unlearn?
- Zico Kolter: Test-time adaptation via the convex conjugate
- Prescriptive solutions in games: from theory to scale
- Aleksandrs Slivkins
Invited Talks
- Invited Talk: Yixin Wang
- Invited Talk #1 - How to communicate your results
- Invited Talk #2 - Collaborations with ML researchers
- Invited Talk: Emma Brunskill
- Invited Talk #3 - Coding best practices
- Invited Talk: Celestine Mendler-Dunner
- Towards a Mathematical Theory of Machine Learning
- Solving the Right Problems: Making ML Models Relevant to Healthcare and the Life Sciences
- Synthetic Control Methods and Difference-In-Differences
- Design for Inference in Drug Discovery and Development
- Predicting and maximizing genomic variant discovery via Bayesian nonparametrics
- Invited Talks 1, Bernhard Schölkopf and David Lopez-Paz
- Jeff Schneider
- Differentiable optimization for control and reinforcement learning
- Open Images: Lessons Learned from Collecting and Annotating 9M images
- Did We Forget about the Canonical Source of Variance in Machine Learning Pipelines?
- Ava Soleimany
- Cyber 101 for Data Scientists and Mathematicians
- Embracing Subjectivity In Machine Learning Benchmarks
- Towards a Common Coordinate Framework: Alignment of Spatially Resolved Omics Data
- Responsible Evaluation Framework
- Discovering RL Algorithms
- Ruth Misener
- The Value Equivalence Principle for Model-Based RL
- Evaluation of ML in Health/Science
- Time Value of Data and AI Strategy
- A Model-Based Reinforcement Learning Wishlist
- Assessing Quality of Information without Ground Truth
- Ethical Challenges of Data Collection & Use in Machine Learning Research
- Challenges and Opportunities in Handling Data Distributional Shift
- Christopher Langmead
- Less Data Can Be More!
- What Can Data-Centric AI Learn from Data Engineering?
- Caroline Uhler
- A Case Study of Real-World Kernel Exploitation
- Policy Gradient: Theory for Making Best Use of It
- General-purpose meta learning
- What will be the ImageNet moment for ABMs?
- Machine-only to human-machine collaboration from practical AI deployments. Ernest Mwebaze
- Neural Scaling of Deep Chemical Models
- Deep neural network approximations for PDEs
- The intersection of simulation-based inference and agent based modelling
- Chinchillas, Flamingos, and Gatos: Few-Shot Learning through Pre-training
- Reservoir Computing for Predicting Complex Network Dynamics
- Adding AI to Agent-Based Models – Applications in infectious disease epidemiology
- How Neural Networks See, Learn and Forget
- Inside and Outside: Ways to Control AI Systems. Fernanda Viegas and Martin Wattenberg
- Program Synthesis, Program Semantics, and Large Language Models
- Creating Human-Computer Partnerships. Wendy Mackay
- Towards Human-Centric Human-Machine Interaction. Nuria Oliver
- How Will Interactive Theorem Provers Develop? Sir Timothy Gowers (Recorded Talk, but with Live Q&A at 13:30!)
- Estimating Policy Functions in Payments Systems Using Reinforcement Learning
- Exploring the Limits of Large Scale Pre-training
- Latent state estimation for agent-based models using data assimilation
- Simplifying and Simplifying Self-Supervised Visual Representation Pre-Training
- Physics-infused learning with ABM
- Unified and Efficient Multimodal Pretraining across Vision and Language
- TBA
- Benefits and Challenges of Pre-training for Environmental Monitoring
- TBA
Invited Talk; In-people
Invited Talk; Livestreameds
Invited Talks
Invited speakers
Invited talks
- A hierarchical representation learning approach for source separation, transcription, and music generation
- Frontiers and challenges in music audio generation
- Invited talks 2, Christina Heinze-Deml and Marzyeh Ghassemi
- Cooperative conversational AI
- Invited talks 3, Amy Zhang, Rich Zemel and Liting Sun
- Self-supervised learning for speech generation
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Deriving modular inductive biases from the principle of independent mechanisms
- Reinforcement learning in continuous-time and space
- Generative Modeling with Stochastic Differential Equations
- ResNet after all? How (not) to design continuous neural network architectures
- Continuous vs. Discrete Optimization of Deep Neural Networks
Keynotes
- Neuroscience & AI: Towards Bio-Inspired Artificial Agents
- On the Decision Support Systems Based on AI for Highly Complex Applications: Health & Defense
- Speech Recognition & Synthesis for Language in Low Data Regimes: Learning from Few Speakers using Multilingual Models
- Three Frontiers of Responsible Machine Learning
- Keynote 1 by Mihaela van der Schaar
- Keynote 2 by Mark Dredze
- The Memory of Persistence
- Artificial Adversarial Intelligence
- The Data-Centric AI Competition
- Opening Keynote: Cognitive Science of Reasoning
- Keynote 3 by Judy Wawira Gichoya
- Keynote 4 by Olga Troyanskaya
- A Brief History of Geometric Data Science
- Keynote 5 by Laura Rosella
- Keynote 6 by Ziad Obermeyer
- An Open Conversation about Joint Data and Model Quality: Metrics, Tools, Practices
- Equivariant Machine Learning with Classical Invariant Theory
- A Practitioner Perspective on ML for Cybersecurity
- Organizing memories for generalization in complementary learning systems
- Recent Advances in Equivariant Learning
- Melika Payvand: Brain-inspired hardware and algorithm co-design for low power online training on the edge
- Responsible Decision-Making in Batch RL Settings
- Alexander Keller: How Computer Graphics advances Hardware Aware Efficient Training
- "Using WaveNet to reunite speech-impaired users with their original voices" (invited talk)
- Robust Multivalid Uncertainty Quantification
- Damien Querlioz: Memory-Centric Machine Learning
- Fabien Cardinaux: DNN Quantization with Mixed Precision and Trained Lookup Tables
- "Fundamental advances in understanding nonverbal behavior" (invited talk)
- Tien-Ju Yang: Neural Network Design and Training for Efficient On-Device Learning
- Dimension Reduction Tools and Their Use in Responsible Data Understanding in Dynamic Environments
- Jian Tang: Neural Bellman-Ford Networks: An Efficient and General Path-based Method for Link Prediction based on GNNs
- Explanations in Whose Interests?
- "Neurosymbolic AI for Sentiment Analysis" (invited talk)
- Exposure-Aware Recommendation using Contextual Bandits
- Modeling Recommender Ecosystems - Some Considerations
Keynote Talks
- Adriana Schulz, University of Washington
- Low-Communication Algorithms for Private Federated Data Analysis
- Karl DD Willis, Autodesk
- Nobuyuki Umetani, University of Tokyo
- Renaud Danhaive, Spacemaker AI
- Iro Armeni, ETH - Zurich
- Adam Goodrich, Procedural Worlds
- Mark Fuge, University of Maryland
- Martha Tsigkari and Sherif Eltarabishy, Foster + Partners
- Private Mean Estimation with Connections to Robustness
- Alan Aspuru-Guzik, University of Toronto
- Ranjitha Kumar, University of Illinois
- Refik Anadol
- Debora S Marks, Harvard Medical School
- Gevorg Grigoryan, Generate Biomedicines
Lightning Talks
Live / interactive sessions
Live Q/A sessions
Live Talks
- Opening Remarks
- Michael I. Jordan: Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
- Zhimei Ren: Sensitivity Analysis of Individual Treatment Effects: A Robust Conformal Inference Approach
- Yao Xie: Conformal prediction intervals and sets for time-series
- Insup Lee: PAC Prediction Sets: Theory and Applications
- Rina Barber: Conformal prediction beyond exchangeability
- Closing Remarks
Live introes
Live panels over zoom
Live presentations
Mentorship Program Presentations
Openings
Opening Remarks
Opening remarks
Orals
- Tackling covariate shift with node-based Bayesian neural networks
- Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
- Exact Optimal Accelerated Complexity for Fixed-Point Iterations
- Online Learning for Min Sum Set Cover and Pandora’s Box
- Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
- Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
- Bounding Training Data Reconstruction in Private (Deep) Learning
- Equivariant Diffusion for Molecule Generation in 3D
- Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
- Unified Scaling Laws for Routed Language Models
- Tractable Uncertainty for Structure Learning
- To Smooth or Not? When Label Smoothing Meets Noisy Labels
- Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems
- Batched Dueling Bandits
- Learning Mixtures of Linear Dynamical Systems
- Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
- Robustness Implies Generalization via Data-Dependent Generalization Bounds
- Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
- Monarch: Expressive Structured Matrices for Efficient and Accurate Training
- Path-Gradient Estimators for Continuous Normalizing Flows
- Online Active Regression
- Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
- Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
- data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
- Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation
- Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model
- Offline RL Policies Should Be Trained to be Adaptive
- Individual Preference Stability for Clustering
- POEM: Out-of-Distribution Detection with Posterior Sampling
- H-Consistency Bounds for Surrogate Loss Minimizers
- Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes
- Cooperative Online Learning in Stochastic and Adversarial MDPs
- Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
- FedNest: Federated Bilevel, Minimax, and Compositional Optimization
- Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
- Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
- Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations
- Minimum Cost Intervention Design for Causal Effect Identification
- Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
- Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models
- Nonparametric Involutive Markov Chain Monte Carlo
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces
- How Tempering Fixes Data Augmentation in Bayesian Neural Networks
- A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes
- Adapting to Mixing Time in Stochastic Optimization with Markovian Data
- A new similarity measure for covariate shift with applications to nonparametric regression
- Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
- Stable Conformal Prediction Sets
- Learning inverse folding from millions of predicted structures
- REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
- Robust Training of Neural Networks Using Scale Invariant Architectures
- Privacy for Free: How does Dataset Condensation Help Privacy?
- Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
- BAMDT: Bayesian Additive Semi-Multivariate Decision Trees for Nonparametric Regression
- Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
- Bayesian Continuous-Time Tucker Decomposition
- Tight and Robust Private Mean Estimation with Few Users
- Generative Trees: Adversarial and Copycat
- 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
- RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests
- Planning with Diffusion for Flexible Behavior Synthesis
- Generating 3D Molecules for Target Protein Binding
- Active fairness auditing
- Robustness Verification for Contrastive Learning
- A Dynamical System Perspective for Lipschitz Neural Networks
- Function-space Inference with Sparse Implicit Processes
- Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
- Agnostic Learnability of Halfspaces via Logistic Loss
- Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models.
- A General Recipe for Likelihood-free Bayesian Optimization
- Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
- Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
- Re-evaluating Word Mover's Distance
- Causal Dynamics Learning for Task-Independent State Abstraction
- Adversarially trained neural representations are already as robust as biological neural representations
- The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation
- Not All Poisons are Created Equal: Robust Training against Data Poisoning
- LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood
- First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
- The Importance of Non-Markovianity in Maximum State Entropy Exploration
- Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling
- Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models
- Overcoming Oscillations in Quantization-Aware Training
- G-Mixup: Graph Data Augmentation for Graph Classification
- Random Gegenbauer Features for Scalable Kernel Methods
- ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
- It’s Raw! Audio Generation with State-Space Models
- The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
- Label Ranking through Nonparametric Regression
- Causal Imitation Learning under Temporally Correlated Noise
- On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming
- UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees
- Learning Bellman Complete Representations for Offline Policy Evaluation
- Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning
- Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints
- Generalised Policy Improvement with Geometric Policy Composition
- Sublinear-Time Clustering Oracle for Signed Graphs
- Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
- Toward Compositional Generalization in Object-Oriented World Modeling
- Do Differentiable Simulators Give Better Policy Gradients?
- Causal Conceptions of Fairness and their Consequences
- Bayesian Model Selection, the Marginal Likelihood, and Generalization
- Deletion Robust Submodular Maximization over Matroids
- A Convergent and Dimension-Independent Min-Max Optimization Algorithm
- Adversarially Trained Actor Critic for Offline Reinforcement Learning
- Large Batch Experience Replay
- From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
- Generalized Strategic Classification and the Case of Aligned Incentives
- Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning
- Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization
- Anarchic Federated Learning
- Measuring Representational Robustness of Neural Networks Through Shared Invariances
- A Simple yet Universal Strategy for Online Convex Optimization
- Do More Negative Samples Necessarily Hurt In Contrastive Learning?
- UniRank: Unimodal Bandit Algorithms for Online Ranking
- An Analytical Update Rule for General Policy Optimization
- Optimal Algorithms for Mean Estimation under Local Differential Privacy
- Online Decision Transformer
- Contributed Talk 1: When does dough become a bagel?Analyzing the remaining mistakes on ImageNet
- GaMPEN: An ML Framework for Estimating Galaxy Morphological Parameters and Quantifying Uncertainty
- Contributed Talk 2: MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts
- Unsupervised Learning for Stellar Spectra with Deep Normalizing Flows
- Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation
- Strong Lensing Source Reconstruction Using Continuous Neural Fields
- Learning Security Strategies through Game Play and Optimal Stopping
- Adversarial Cheap Talk
- OOD-CV: A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts
- Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
- Growing ObjectNet: Adding speech, VQA, occlusion, and measuring dataset difficulty
- Classifiers Should Do Well Even on Their Worst Classes
- Towards Systematic Robustness for Scalable Visual Recognition
- Lost in Translation: Modern Image Classifiers still degrade even under simple Translations
- Evaluating Model Robustness to Patch Perturbations
- ImageNet-Cartoon and ImageNet-Drawing: two domain shift datasets for ImageNet
- CCC: Continuously Changing Corruptions
- SI-Score
- ImageNet-D: A new challenging robustness dataset inspired by domain adaptation
- The Semantic Shift Benchmark
- 3D Common Corruptions for Object Recognition
- Reconstructing the Universe with Variational self-Boosted Sampling
- Detecting Anomalies in Encrypted EV Charging Control Protocol Using a Hybrid LSTM Autoencoder-OCSVM Model
- TNT: Vision Transformer for Turbulence Simulations
- CyberEnt: Extracting Domain Specific Entities from Cybersecurity Text
- Galaxy Merger Reconstruction with Equivariant Graph Normalizing Flows
- Hybrid Physical-Neural ODEs for Fast N-body Simulations
- Uncovering dark matter density profiles in dwarf galaxies with graph neural networks
- Contributed Talk 3: ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
- Multimodal Masked Autoencoders Learn Transferable Representations
- Near-optimal Regret for Adversarial MDP with Delayed Bandit Feedback
- Contextual Inverse Optimization: Offline and Online Learning
- Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Prior
- Giving Complex Feedback in Online Student Learning with Meta-Exploration
- Threshold Bandit Problem with Link Assumption between Pulls and Duels
- Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round
- Plex: Towards Reliability using Pretrained Large Model Extensions
- ActiveHedge: Hedge meets Active Learning
- Learning to Solve PDE-constrained Inverse Problems with Graph Networks
- Understanding the evolution of tumours using hybrid deep generative models
- Efficient Continuous Spatio-Temporal Simulation with Graph Spline Networks
- A Density Functional Recommendation Approach for Accurate Predictions of Vertical Spin Splitting of Transition Metal Complexes
Oral (Contributed)s
- Evology: an Empirically-Calibrated Market Ecology Agent-Based Model for Trading Strategy Search
- Exploring social theory integration in agent-based modelling using multi-objective grammatical evolution
- Differentiable agent-based epidemiological modeling for end-to-end learning
- Estimating the Impact of Coordinated Inauthentic Behavior on Content Recommendations in Social Networks
Panels
Panel Discussions
Panel Remarks (Backup)s
Paper Presentations
Posters
- Backward Reachability for Neural Feedback Loops
- Model Transferability With Responsive Decision Subjects
- What is a Good Metric to Study Generalization of Minimax Learners?
- Toward Efficient Robust Training against Union of Lp Threat Models
- On the interplay of adversarial robustness and architecture components: patches, convolution and attention
- Towards Optimal Randomized Smoothing: A Semi-Infinite Linear Programming Approach
- Hypergraph Topological Features for Autoencoder-Based Intrusion Detection for Cybersecurity Data
- Exploiting and Defending Against the Approximate Linearity of Apple’s NeuralHash
- Reducing Exploitability with Population Based Training
- Using Machine Learning to Infer Plausible and Undetected Cyber Threat, Vulnerability and Mitigation Relationships
- An Artificial Intelligence-Enabled Framework for Optimizing the Dynamic Cyber Vulnerability Management Process
- A High Fidelity Cybersecurity Dataset for Attack Modeling
- Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
- Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems
- Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
- ACD-G: Enhancing Autonomous Cyber Defence Agent Generalisation Through Graph Embedded Network Representation
- Do Perceptually Aligned Gradients Imply Adversarial Robustness?
- Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
- Catastrophic overfitting is a bug but also a feature
- Fair Universal Representations using Adversarial Models
- Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
- Early Layers Are More Important For Adversarial Robustness
- Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free
- Attacking Adversarial Defences by Smoothing the Loss Landscape
- Sound randomized smoothing in floating-point arithmetics
- Robustness in deep learning: The width (good), the depth (bad), and the initialization (ugly)
- Riemannian data-dependent randomized smoothing for neural network certification
- Adversarial robustness of $\beta-$VAE through the lens of local geometry
- ``Why do so?'' --- A practical perspective on adversarial machine learning
- Adversarial Estimation of Riesz Representers
- Saliency Guided Adversarial Training for Tackling Generalization Gap with Applications to Medical Imaging Classification System
- Self-Destructing Models: Increasing the Costs of Harmful Dual Uses in Foundation Models
- Illusionary Attacks on Sequential Decision Makers and Countermeasures
- Can we achieve robustness from data alone?
- Gradient-Based Adversarial and Out-of-Distribution Detection
- Investigating Why Contrastive Learning Benefits Robustness against Label Noise
- Layerwise Hebbian/anti-Hebbian (HaH) Learning In Deep Networks: A Neuro-inspired Approach To Robustness
- Efficient and Effective Augmentation Strategy for Adversarial Training
- Robust Empirical Risk Minimization with Tolerance
- Towards Out-of-Distribution Adversarial Robustness
- Reducing Exploitability with Population Based Training
- RUSH: Robust Contrastive Learning via Randomized Smoothing
- Optimal Parameter-free Online Learning with Switching Cost
- Challenging Common Assumptions in Convex Reinforcement Learning
- Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
- Provably Correct SGD-based Exploration for Linear Bandit
- You Only Live Once: Single-Life Reinforcement Learning via Learned Reward Shaping
- Stochastic Rising Bandits for Online Model Selection
- Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP
- Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
- Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning
- Dynamical Linear Bandits for Long-Lasting Vanishing Rewards
- Online Learning with Off-Policy Feedback
- On Adaptivity and Confounding in Contextual Bandit Experiments
- Unimodal Mono-Partite Matching in a Bandit Setting
- Beyond IID: data-driven decision-making in heterogeneous environments
- Big Control Actions Help Multitask Learning of Unstable Linear Systems
- Adversarial Attacks Against Imitation and Inverse Reinforcement Learning
- Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits
- Interaction-Grounded Learning with Action-inclusive Feedback
- On the Importance of Critical Period in Multi-stage Reinforcement Learning
- ActiveHedge: Hedge meets Active Learning
- Near-optimal Regret for Adversarial MDP with Delayed Bandit Feedback
- Giving Complex Feedback in Online Student Learning with Meta-Exploration
- Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round
- Threshold Bandit Problem with Link Assumption between Pulls and Duels
- Contextual Inverse Optimization: Offline and Online Learning
- Parameter Estimation in Realistic Binary Microlensing Light Curves with Neural Controlled Differential Equation
- Full-Sky Gravitational Lensing Simulations Using Generative Adversarial Networks
- An Unsupervised Learning Approach for Quasar Continuum Prediction
- Astroconformer: Inferring Surface Gravity of Stars from Stellar Light Curves with Transformer
- Don't Pay Attention to the Noise: Learning Self-supervised Representations of Light Curves with a Denoising Time Series Transformer
- Fast Estimation of Physical Galaxy Properties using Simulation-Based Inference
- Reduced Order Model for Chemical Kinetics: A case study with Primordial Chemical Network
- Robust Simulation-Based Inference with Bayesian Neural Networks
- Galaxies on graph neural networks: towards robust synthetic galaxy catalogs with deep generative models
- Estimating Cosmological Constraints from Galaxy Cluster Abundance using Simulation-Based Inference
- Bayesian Neural Networks for classification tasks in the Rubin big data era
- Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks
- SIMBIG: Likelihood-Free Inference of Galaxy Clustering
- Automated discovery of interpretable gravitational-wave population models
- Accelerated Galaxy SED Modeling using Amortized Neural Posterior Estimation
- Scalable Bayesian Inference for Detection and Deblending in Astronomical Images
- Toward Galaxy Foundation Models with Hybrid Contrastive Learning
- DeepBench: A library for simulating benchmark datasets for scientific analysis
- Calibrated Predictive Distributions for Photometric Redshifts
- Learnable wavelet neural networks for cosmological inference
- Learning Galaxy Properties from Merger Trees
- LINNA: Likelihood Inference Neural Network Accelerator
- Population-Level Inference of Strong Gravitational Lenses with Neural Network-Based Selection Correction
- Pixelated Reconstruction of Gravitational Lenses using Recurrent Inference Machines
- Autoencoding Galaxy Spectra
- A Convolutional Neural Network for Supernova Time-Series Classification
- Neural Posterior Estimation with Differentiable Simulator
- Learning useful representations for radio astronomy “in the wild” with contrastive learning
- Probabilistic Dalek - Emulator framework with probabilistic prediction for supernova tomography
- On Estimating ROC Arc Length and Lower Bounding Maximal AUC for Imbalanced Classification
- Towards Better Understanding of Self-Supervised Representations
- Causal Balancing for Domain Generalization
- In the Eye of the Beholder: Robust Prediction with Causal User Modeling
- Causal Prediction Can Induce Performative Stability
- Evaluating and Improving Robustness of Self-Supervised Representations to Spurious Correlations
- Domain Adaptation under Open Set Label Shift
- Towards Domain Adversarial Methods to Mitigate Texture Bias
- Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
- Invariance Discovery for Systematic Generalization in Reinforcement Learning
- Probing Classifiers are Unreliable for Concept Removal and Detection
- Are We Viewing the Problem of Robust Generalisation through the Appropriate Lens?
- Detecting Shortcut Learning using Mutual Information
- Selection Bias Induced Spurious Correlations in Large Language Models
- Invariance Principle Meets Out-of-Distribution Generalization on Graphs
- Latent Variable Models for Bayesian Causal Discovery
- Understanding Generalization and Robustess of Learned Representations of Chaotic Dynamical Systems
- Policy Architectures for Compositional Generalization in Control
- Representation Learning as Finding Necessary and Sufficient Causes
- Unsupervised Learning under Latent Label Shift
- A Study of Causal Confusion in Preference-Based Reward Learning
- Learning to induce causal structure
- Repeated Environment Inference for Invariant Learning
- Finding Spuriously Correlated Visual Attributes
- BARACK: Partially Supervised Group Robustness With Guarantees
- Towards Environment-Invariant Representation Learning for Robust Task Transfer
- Doubly Right Object Recognition
- SimpleSpot and Evaluating Systemic Errors using Synthetic Image Datasets
- "Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
- Characterizing Datapoints via Second-Split Forgetting
- Invariant and Transportable Representations for Anti-Causal Domain Shifts
- Contrastive Adapters for Foundation Model Group Robustness
- HyperInvariances: Amortizing Invariance Learning
- Conditional Distributional Invariance through Implicit Regularization
- Enhancing Unit-tests for Invariance Discovery
- Diversify and Disambiguate: Learning from Underspecified Data
- Unsupervised Causal Generative Understanding of Images
- Causal Discovery using Model Invariance through Knockoff Interventions
- Using causal modeling to analyze generalization of biomarkers in high-dimensional domains: a case study of adaptive immune repertoires
- The Importance of Background Information for Out of Distribution Generalization
- Self-Supervision on Images and Text Reduces Reliance on Visual Shortcut Features
- Out-of-Distribution Failure through the Lens of Labeling Mechanisms: An Information Theoretic Approach
- How much Data is Augmentation Worth?
- On the Generalization and Adaption Performance of Causal Models
- Learning Switchable Representation with Masked Decoding and Sparse Encoding
- Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization
- Towards Group Robustness in the Presence of Partial Group Labels
- Towards Multi-level Fairness and Robustness on Federated Learning
- Learning Debiased Classifier with Biased Committee
- Causal Omnivore: Fusing Noisy Estimates of Spurious Correlations
- Robust Calibration with Multi-domain Temperature Scaling
- A Unified Causal View of Domain Invariant Representation Learning
- Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
- Evaluating Robustness to Dataset Shift via Parametric Robustness Sets
- Causally motivated multi-shortcut identification and removal
- How robust are pre-trained models to distribution shift?
- Understanding Rare Spurious Correlations in Neural Networks
- Optimization-based Causal Estimation from Heterogenous Environments
- Automated Invariance Testing for Machine Learning Models Using Sparse Linear Layers
- Fairness and robustness in anti-causal prediction
- Are Vision Transformers Robust to Spurious Correlations ?
- DAFT: Distilling Adversarially Fine-tuned teachers for OOD Robustness
- On the nonlinear correlation of ML performance across data subpopulations
- Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty
- OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization
- Linear Connectivity Reveals Generalization Strategies
- SelecMix: Debiased Learning by Mixing up Contradicting Pairs
- Optimizing maintenance by learning individual treatment effects
- On Quantum Computing for Neural Network Robustness Verification
- Verification-friendly Networks: the Case for Parametric ReLUs
- Formal Privacy Guarantees for Neural Network queries by estimating local Lipschitz constant
- Sound randomized smoothing in floating-point arithmetics
- Optimized Symbolic Interval Propagation for Neural Network Verification
- Sound and Complete Verification of Polynomial Networks
- Safety Verification and Repair of Deep Neural Networks
- Robustness Verification for Contrastive Learning
- CertiFair: A Framework for Certified Global Fairness of Neural Networks
- Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State Backreachability
- Programmatic Reinforcement Learning with Formal Verification
- Toward Certified Robustness Against Real-World Distribution Shifts
- Verification of Neural Ordinary Differential Equations using Reachability Analysis
- Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach
- Improving adversarial robustness via joint classification and multiple explicit detection classes
- ReCIPH: Relational Coefficients for Input Partitioning Heuristic
- Certified Robustness Against Natural Language Attacks by Causal Intervention
- Efficient Continuous Spatio-Temporal Simulation with Graph Spline Networks
- LinkBERT: Language Model Pretraining with Document Link Knowledge
- Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Biomolecular Structures and Interaction Networks
- Understanding the evolution of tumours using hybrid deep generative models
- On the Relationships between Graph Neural Networks for the Simulation of Physical Systems and Classical Numerical Methods
- Intelligent Digital Twins can Accelerate Scientific Discovery and Control Complex Multi-Physics Processes
- Reinforced Genetic Algorithm for Structure-based Drug Design
- Improving Subgraph Representation Learning via Multi-View Augmentation
- Path Integral Stochastic Optimal Control for Sampling Transition Paths
- Evaluating Self-Supervised Learned Molecular Graphs
- Unifying physical systems’ inductive biases in neural ODE using dynamics constraints
- PowerGraph: Using neural networks and principal components to determine multivariate statistical power trade-offs
- From Kepler to Newton: Explainable AI for Science Discovery
- LAST: Latent Space Assisted Adaptive Sampling for Protein Trajectories
- One-Shot Transfer Learning of Physics-Informed Neural Networks
- Weakly Supervised Inversion of Multi-physics Data for Geophysical Properties
- How Much of the Chemical Space Has Been Explored? Selecting the Right Exploration Measure for Drug Discovery
- No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit
- Predicting generalization with degrees of freedom in neural networks
- Unsupervised Discovery of Inertial-Fusion-Relevant Plasma Physics using Differentiable Kinetic Simulations
- MultiScale MeshGraphNets
- Learning to Solve PDE-constrained Inverse Problems with Graph Networks
- Curvature-informed multi-task learning for graph networks
- Neural Basis Functions for Accelerating Solutions to high Mach Euler Equations
- MAgNet: Mesh Agnostic Neural PDE Solver
- Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers
- Differentiable Physics Simulations with Contacts: Do They Have Correct Gradients w.r.t. Position, Velocity and Control?
- Transform Once: Efficient Operator Learning in Frequency Domain
- Provable Concept Learning for Interpretable Predictions Using Variational Autoencoders
- Recovering Stochastic Dynamics via Gaussian Schrödinger Bridges
- Towards Learning Self-Organized Criticality of Rydberg Atoms using Graph Neural Networks
- Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks
- Pre-training Transformers for Molecular Property Prediction Using Reaction Prediction
- Featurizations Matter: A Multiview Contrastive Learning Approach to Molecular Pretraining
- Sample Efficiency Matters: Benchmarking Molecular Optimization
- The Bearable Lightness of Big Data: Towards Massive Public Datasets in Scientific Machine Learning
- DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks
- Target-aware Molecular Graph Generation
- Pre-training Graph Neural Networks for Molecular Representations: Retrospect and Prospect
- Mesh-Independent Operator Learning for Partial Differential Equations
- Removing parasitic elements from Quantum Optical Coherence Tomography data with Convolutional Neural Networks
- Multiresolution Equivariant Graph Variational Autoencoder
- Multiresolution Matrix Factorization and Wavelet Networks on Graphs
- Quantum Neural Architecture Search with Quantum Circuits Metric and Bayesian Optimization
- Variational Inference for Soil Biogeochemical Models
- Centralized vs Individual Models for Decision Making in Interconnected Infrastructure
- An Optical Pulse Stacking Environment and Reinforcement Learning Benchmarks
- $O(N^2)$ Universal Antisymmetry in Fermionic Neural Networks
- GAUCHE: A Library for Gaussian Processes in Chemistry
- Bias in the Benchmark: Systematic experimental errors in bioactivity databases confound multi-task and meta-learning algorithms
- Deep Learning and Symbolic Regression for Discovering Parametric Equations
- A Density Functional Recommendation Approach for Accurate Predictions of Vertical Spin Splitting of Transition Metal Complexes
- Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors
- Perspectives on Incorporating Expert Feedback into Model Updates
- Machine Explanations and Human Understanding
- Argumentative reward learning: Reasoning about human preferences
- Human-AI Collaborative Decision-Making: Beyond Learning to Defer
- Human-machine collaboration for reusable and scalable models for remote sensing imagery analysis
- Counterfactual Inference of Second Opinions
- A Human-Centric Assessment Framework for AI
- Predicting Human Similarity Judgments Using Large Language Models
- CrowdPlay: Crowdsourcing demonstrations for learning human-AI interaction
- Elicit: A Framework for Human-in-the-Loop High-Precision Information Extraction from Text Documents
- Training Novices: The Role of Human-AI Collaboration and Knowledge Transfer
- Towards Effective Case-Based Decision Support with Human-Compatible Representations
- Adaptive Out-of-Distribution Detection with Human-in-the-Loop
- Learning to Play with the Machines in Social Science Research: Bringing the Theory Back In
- A Framework for Learning to Request Rich and Contextually Useful Information from Humans
- Effects of Algorithmic Fairness Constraints on Human Hiring Decisions
- Diverse Concept Proposals for Concept Bottleneck Models
- A Human-Centric Take on Model Monitoring
- On the Calibration of Learning to Defer to Multiple Experts
- The Influence of Explainable Artificial Intelligence: Nudging Behaviour or Boosting Capability?
- Bayesian Weak Supervision via an Optimal Transport Approach
- A Taxonomy Characterizing Human and ML Predictive Decision-making
- How to Talk so Robots will Learn: Instructions, Descriptions, and Alignment
- Effective Offline RL Needs Going Beyond Pessimism: Representations and Distributional Shift
- Hyperbolically Discounted Advantage Estimation for Generalization in Reinforcement Learning
- Deep Policy Generators
- CoMBiNED: Multi-Constrained Model Based Planning for Navigation in Dynamic Environments
- Exploration Hurts in Bandits with Partially Observed Stochastic Contexts
- Exploration in Reward Machines with Low Regret
- Exploring Long-Horizon Reasoning with Deep RL in Combinatorially Hard Tasks
- VIPer: Iterative Value-Aware Model Learning on the Value Improvement Path
- Model-Based Meta Automatic Curriculum Learning
- General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
- An Investigation into the Open World Survival Game Crafter
- Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
- Model-Based Reinforcement Learning with SINDy
- Toward Human Cognition-inspired High-Level Decision Making For Hierarchical Reinforcement Learning Agents
- MoCoDA: Model-based Counterfactual Data Augmentation
- An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning
- Leader-based Decision Learning for Cooperative Multi-Agent Reinforcement Learning
- Recursive History Representations for Unsupervised Reinforcement Learning in Multiple-Environments
- Building a Subspace of Policies for Scalable Continual Learning
- DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning
- Representation Gap in Deep Reinforcement Learning
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
- Giving Feedback on Interactive Student Programs with Meta-Exploration
- When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
- Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions
- Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
- You Can’t Count on Luck: Why Decision Transformers Fail in Stochastic Environments
- Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
- Fast Convergence for Unstable Reinforcement Learning Problems by Logarithmic Mapping
- Self-Referential Meta Learning
- Distributionally Adaptive Meta Reinforcement Learning
- You Only Live Once: Single-Life Reinforcement Learning via Learned Reward Shaping
- Directed Exploration via Uncertainty-Aware Critics
- Adversarial Cheap Talk
- Adaptive Intrinsic Motivation with Decision Awareness
- Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
- Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
- Task Factorization in Curriculum Learning
- SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
- Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization
- Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
- Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation
- MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning
- Simple and near-optimal algorithms for hidden stratification and multi-group learning
- GAPX: Generalized Autoregressive Paraphrase-Identification X
- Generative Gradual Domain Adaptation with Optimal Transport
- Pareto Invariant Risk Minimization
- Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation
- Distribution Shift nested in Web Scraping : Adapting MS COCO for Inclusive Data
- Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction
- ALASCA: Rethinking Label Smoothing for Deep Learning Under Label Noise
- Diversify and Disambiguate: Learning from Underspecified Data
- Back to the Basics: Revisiting Out-of-Distribution Detection Baselines
- Style Balancing and Test-Time Style Shifting for Domain Generalization
- Models Out of Line: A Fourier Lens on Distribution Shift Robustness
- Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
- The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
- A Bias-Variance Analysis of Weight Averaging for OOD Generalization
- Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization
- What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
- Time Series Prediction under Distribution Shift using Differentiable Forgetting
- On the nonlinear correlation of ML performance across data subpopulations
- Data Augmentation vs. Equivariant Networks: A Theoretical Study of Generalizability on Dynamics Forecasting
- Maximum Mean Discrepancy Distributionally Robust Nonlinear Chance-Constrained Optimization with Finite-Sample Guarantee
- DAFT: Distilling Adversarially Fine-tuned teachers for OOD Robustness
- Evaluation of Generative Unsupervised Domain Adaptation in the Absence of Target Labels
- GraphTTA: Test Time Adaptation on Graph Neural Networks
- Adversarial Cheap Talk
- Fairness and robustness in anti-causal prediction
- Plex: Towards Reliability using Pretrained Large Model Extensions
- Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables
- Task Modeling: A Multitask Approach for Improving Robustness to Group Shifts
- A Meta-Analysis of Distributionally Robust Models
- On Feature Learning in the Presence of Spurious Correlations
- Deep ensemble diversity and robustness on classification tasks
- Asymmetry Learning for Counterfactual-invariant Classification in OOD Tasks
- Robust Estimation of Laplacian Constrained Gaussian Graphical Models with Trimmed Non-convex Regularization
- Evaluating Robustness to Dataset Shift via Parametric Robustness Sets
- Improved Medical Out-of-Distribution Detectors For Modality and Semantic Shifts
- AugLoss: A Robust, Reliable Methodology for Real-World Corruptions
- Context Shift from Test Benchmarks to Real-World Production Performance
- Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety
- CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
- Diagnosing Model Performance Under Distribution Shift
- Distributionally Adaptive Meta Reinforcement Learning
- 2 CENTs on continual adaptation: replay & parameter buffers stabilize entropy minimization
- Towards Practicable Sequential Shift Detectors
- Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
- What can we do with just the model? A simple knowledge extraction framework
- Are We Viewing the Problem of Robust Generalisation through the Appropriate Lens?
- Adapting to Shifts in Latent Confounders via Observed Concepts and Proxies
- Positive Unlabeled Contrastive Representation Learning
- Towards Domain Adversarial Methods to Mitigate Texture Bias
- Dynamics of Dataset Bias and Robustness
- Bridging Distribution Shift in Imitation Learning via Taylor Expansions
- Rethinking Multidimensional Discriminator Output for Generative Adversarial Networks
- Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift
- Generative Models with Information-Theoretic Protection Against Membership Inference Attacks
- Availability Attacks on Graph Neural Networks
- Robust Models are less Over-Confident
- Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO
- Distributionally Robust counterfactual Explanations via an End-to-End Training Approach
- Meta-Learning Adversarial Bandits
- Boosting Image Generation via a Robust Classifier
- Why adversarial training can hurt robust accuracy
- Superclass Adversarial Attack
- Individually Fair Learning with One-Sided Feedback
- Multi-Task Federated Reinforcement Learning with Adversaries
- Adversarial Cheap Talk
- Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
- Synthetic Dataset Generation for Adversarial Machine Learning Research
- Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools
Poster (Contributed)s
- Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
- Deep Learning-based Spatially Explicit Emulation of an Agent-Based Simulator for Pandemic in a City
- Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
- A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning
- Risk Perspective Exploration in Distributional Reinforcement Learning
- The AI Macroeconomy: A New Set of Benchmarks for Multiagent Reinforcement Learning Models
- Inferring Relationship using Theory of Mind in Press Diplomacy
- The Robustness of Inverse Reinforcement Learning
Poster Sessions
- [Poster] CNN-based Emotion Recognition from Multimodal Peripheral Physiological Signals
- [Poster] Detecting Objects in Less Response Time for Processing Multimedia Events in Smart Cities
- [Poster] Cancer Health Disparities drivers with BERTopic and Pycaret Evaluation
- [Poster] A Recurrent Neural Network Model of Travel Direction in Humans
- [Poster] Cell Segmentation and Classification in Multispectral Pathology Images, Exploration and Challenges
- [Poster] Non-invasive Stress Monitoring from Video for Semi-Autonomous Systems
- Poster Session 2
- [Poster] Solving Constrained Variational Inequalities via an Interior Point Method
- [Poster] Automated deep lineage tree analysis using a Bayesian single cell tracking approach
- [Poster] Prostate Cancer Malignancy Detection and Localization From MpMRI Using Auto-Deep Learning: One Step Closer to Clinical Utilization
- [Poster] Early identification of Tuta absoluta in tomato plants using deep learning
- [Poster] Neural Networks for Financial Time Series Forecasting
- [Poster] Fast and Accurate Method for the Segmentation of Diabetic Foot Ulcer Images
- [Poster] Interpretable Adversarial Attacks using Frank Wolfe
- [Poster] Automated Adaptive Design in Real Time
- [Poster] Robust task-specific adaption of drug-target interaction models
- [Poster] Mimicking Iterative Learning with Modern Hopfield Networks for Tabular Data
- [Poster] Multi-modal Contrastive Learning with CLOOB
- [Poster] Cross-modal contrastive learning of microscopy image and structure-based representations of molecules
- [Poster] Affects of Remote Learning on Academic Performance of High School Students
- [Poster] Bayesian Optimisation for Active Monitoring of Air Pollution
- [Poster] Fourier-Based Strategies to Improve Ethnic Feature Generation during Visible-to-Thermal Facial Translation
- [Poster] Deep Kernel Learning with Personalized Multi-task Gaussian Processes for Longitudinal Prediction in Alzheimer’s Disease
- [Poster] Robust classification and uncertainty estimation via invariant learning
- [Poster] Explaining structure-activity relationships using locally faithful surrogate models
- [Poster] Discovery Analysis for Machine Learning Model Understanding
- [Poster] Exploration of Artificial Intelligence Algorithms for the Prediction of Genetic Merit in Sheep
- [Poster] Application of Meta-Inverse Reinforcement Learning to Understanding Human Driving Behavior
- [Poster] A Learning-Theoretic Framework for Certified Auditing of Machine Learning Models
- [Poster] Not All Poisons are Created Equal: Robust Training against Data Poisoning
- [Poster] Self–Similarity Priors: Neural Collages as Differentiable Fractal Representations
- [Poster] Learning to Solve PDE-constrained Inverse Problems with Graph Networks
- [Poster] Global Sensitivity Analysis of MAP Inference in Selective Sum-Product Networks
Poster Session + Breaks
Posters
Prerecorded Talks
Presentations
- Introduction and Opening Remarks
- Virtual Mentor Panel
- Closing Remarks
- Introductory Remarks
- Opening Remarks
- Opening Remarks
- Best Student Paper Award
- Closing Remarks and Poster Session Kickoff
- Closing remarks
- Welcoming remarks and introduction
- Invited talk #1 Cynthia Rudin (Title: Almost Matching Exactly for Interpretable Causal Inference)
- Invited talk #2 James Zou (Title: Machine learning to make clinical trials more efficient and diverse)
- Poster spotlight #1
- Invited talk #3 Rich Caruana. Talk Title: Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning for Healthcare
- Invited talk #4 Been Kim (Title: How to stop worry about interpretability, and start making progress)
- Invited talk #5 Elliot K Fishman, M.D. Title: The Early Detection of Pancreatic Cancer: The Role of AI
- Invited talk #6 Alan Yuille (Title: The Felix Project: Deep Networks To Detect Pancreatic Neoplasms)
- Poster spotlight #2
- Best paper award presentation
- Invited talk #7 Noa Dagan, M.D. and Noam Barda, M.D. Title: Model explainability - the perspective of implementing prediction models for patient care in a large healthcare organization)
- Invited talk #8 Atlas Wang. Title: “Free Knowledge” in Chest X-rays: Contrastive Learning of Images and Their Radiomics
- Poster spotlight #3
- Closing remarks
Presentation (Sponsor)s
Programs
Q&AS
- GraphWorld Q/A
- Discrete optimization Q/A
- Robust GNNs Q/A
- TF-GNN Q/A
- Graph Mining Q/A
- Graph Building Q/A
- Clustering Q/A
- Private Algorithms Q/A
- Q&A for Maria-Jose Escobar
- Q&A
- Q&A for Olga Lucia
- Q&A
- Q&A
- Q&A
- Q&A
- Q&A for Moacir
- Q&A
- Q&A
- Q&A
- Q&A for CJ
- Q&A
- Q&A II
- Q&A for Maria
- Q&A for Ramesh
- Predicting and maximizing genomic variant discovery via Bayesian nonparametrics
- Generative power of a protein language model trained on multiple sequence alignments
- Towards a Common Coordinate Framework: Alignment of Spatially Resolved Omics Data
- BayesTME: A reference-free Bayesian method for end-to-end analysis of spatial transcriptomic data
- DIISCO: Dynamic Intercellular Interactions in Single Cell transcriptOmics
- SPACE-GM: geometric deep learning of disease-associated microenvironments from multiplex spatial protein profiles
- Q&A for Ernest
- Q&A for Fernanda and Martin
- Q&A for Wendy
- Q&A for Nuria
Q/AS
- Q/A: David Held
- Q/A: Ivan Istomin
- Q/A: Melanie Zeilinger
- Q/A: Paper 16: Constrained Model-based Reinforcement Learning via Robust Planning
- Invited talks 2 Q/A, Christina and Marzyeh
- Q/A: Invited Speaker: Peter Stone
- Q/A: Todd Hester
- Q/A: Chelsea Finn
- Q/A: Andrea Bajcsy
- Q/A: Jeff Schneider
- Q/A Sergey Levine
Q/A sessions
Questions
Recorded Flash Talks
Recorded Spotlight Talks
Remote talks
Sessions
- Mentoring Session
- Social Aspects
- Probabilistic Methods/Applications
- Reinforcement Learning
- Deep Learning: Robustness
- APP: Language, Speech and Dialog
- Optimization: Convex
- Theory: Online Learning/Bandits
- Deep Learning: Generative Models/Autoencoders
- Transfer/Multitask/Meta Learning
- Deep Learning
- DL: Algorithms
- SA: Accountability, Transparency and Interpretability
- APP: Computer Vision
- Theory
- MISC: Unsupervised and Semi-supervised Learning
- PM: Gaussian Processes
- Reinforcement Learning: Deep/Batch/Offline
- Theory: Bandits/RL/Everything Else
- Optimization
- DL: Graph Neural Networks
- Deep Learning
- MISC: Causality
- SA: Trustworthy Machine Learning
- T: Learning/Deep Learning Theory
- APP: Neuroscience, Cognitive Science
- PM: Monte Carlo and Sampling Methods
- OPT: Non-Convex
- Theory
- RL: Multi-agent
- DL: Sequential Models
- Deep Learning
- MISC: General Machine Learning Techniques
- T: Learning Theory/Domain Adaptation
- Applications
- PM: Variational Inference/Bayesian Models and Methods
- Reinforcement Learning: Deep RL
- DL: Theory
- T: Game Theory/RL/Planning
- Social Aspects/MISC
- OPT: First Order
- Deep Learning/APP:Computer Vision
- Theory
- APP: Chemistry and Drug Discovery
- MISC: Representation Learning/Causality
- PM: Bayesian Models and Methods
- Reinforcement Learning
- SA: Trustworthy Machine Learning
- DL: Robustness
- DL: Robustness
- T: Online Learning and Bandits/Learning Theory
- Deep Learning
- Theory
- Applications
- Reinforcement Learning
- DL: Algorithms
- SA: Privacy-preserving Statistics and Machine Learning
- Deep Learning/Optimization
- Deep Learning/MISC
- Miscellaneous Aspects of Machine Learning/Reinforcement Learning
- Deep Learning/Optimization
- Deep Learning
- T: Bandits/Online Learning/Reinforcement Learning
- APP: Physics/Computer Vision
- Reinforcement Learning
- DL: Generative Models and Autoencoders
- Theory/Social Aspects
- Miscellaneous Aspects of Machine Learning
- Optimization/Reinforcement Learning
- Deep Learning/Optimization
- MISC/Deep Learning
- Deep Learning: SSL/GNN
- Theory: Game Theory and Optimization
- Deep Learning: Attention Mechanisms
- Applications
- Reinforcement Learning
- MISC/Social Aspects
- Deep Learning/MISC
- Probabilistic Methods/MISC
- Optimization/Reinforcement Learning
- Reinforcement Learning
- Deep Learning
- T: Online Learning and Bandits
- Deep Learning
- Applications/Optimization
- Applications/MISC
- Optimization/Reinforcement Learning
- Reinforcement Learning/Optimization
- Optimization/Probabilistic Methods
- Social Aspects/Optimization
- Optimization/Theory
Short Talks
- Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
- Metadata Representations for Queryable ML Model Zoos
- Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
- Interpretable Distribution Shift Detection using Optimal Transport
- Data Budgeting for Machine Learning
- Data Sculpting: Interpretable Algorithm for End-to-End Cohort Selection
- Data Augmentation Techniques for Speech Error Correction
- Data-Centric AI Infra 2.0
- Beyond Hard Labels: Investigating data label distributions
- An Operational Metrics Framework for ML Data
- An Empirical Study of Modular Bias Mitigators and Ensembles
- A Self-Supervised Automatic Post-Editing Data Generation Tool
- Robustar: Interactive Toolbox Supporting Precise Data Annotation for Robust Vision Learning
- Toolbox for Visualizing Effects of Data Instances on Decision Boundaries
- Not All Poisons are Created Equal: Robust Training against Data Poisoning
- An Adaptive Deep Clustering Pipeline to Inform Text Labeling at Scale
- Model-Agnostic Label Quality Scoring to Detect Real-World Label Errors
- Open Coding for Machine Learning Data
- Radically Lower Data-Labeling Costs for Document Extraction Models with Selective Labeling
- Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
- FORML: Learning to Reweight Data for Fairness
- GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language
- Robust Synthetic GNN Benchmarks with GraphWorld
- Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge
- MRCLens: an MRC Dataset Bias Detection Toolkit
- FairGen: Fair Synthetic Data Generation
- LAVA: Language Audio Vision Alignment for Data-Efficient Contrastive Learning on Video Data
- Infinite Recommendation Networks: A Data-Centric Approach
- Revisiting Hotels-50K and Hotel-ID
- TMED 2: A Dataset for Semi-Supervised Classification of Echocardiograms
- GreenDB - A Data Set and Benchmark for Extraction of Sustainability Information of Consumer Goods
- DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations
Short talks
Socials
- Designing an RL system toward AGI
- Quantum ML
- Commonsense Knowledge Discovery and Acquisition
- Black in AI and Queer in AI Joint Social Event
- Interdisciplinary ML Mixer
- The ICML Debate: Will Progress towards Achieving AI be Mostly Driven by Engineering or Science?
- Mental Health in ML Academia
- Crazy and Fun Ideas ICML’22
- How to Negotiate Industry Offers in AI
Sponsor Data Challenge presentations
Sponsor Events
Spotlights
- Differentially Private Approximate Quantiles
- Dynamic Regret of Online Markov Decision Processes
- Certified Robustness Against Natural Language Attacks by Causal Intervention
- Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling
- Multi-Task Learning as a Bargaining Game
- Structural Entropy Guided Graph Hierarchical Pooling
- Fairness Interventions as (Dis)Incentives for Strategic Manipulation
- On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
- A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing
- ButterflyFlow: Building Invertible Layers with Butterfly Matrices
- Frustratingly Easy Transferability Estimation
- Self-Supervised Representation Learning via Latent Graph Prediction
- Robust Models Are More Interpretable Because Attributions Look Normal
- Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
- On the Learning of Non-Autoregressive Transformers
- Controlling Conditional Language Models without Catastrophic Forgetting
- Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
- DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
- Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
- Provable Reinforcement Learning with a Short-Term Memory
- Latent Diffusion Energy-Based Model for Interpretable Text Modelling
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- A Difference Standardization Method for Mutual Transfer Learning
- Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
- A Joint Exponential Mechanism For Differentially Private Top-$k$
- Why the Rich Get Richer? On the Balancedness of Random Partition Models
- Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
- ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
- UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
- Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
- Smoothed Adversarial Linear Contextual Bandits with Knapsacks
- Structure-preserving GANs
- Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
- Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
- Transfer Learning In Differential Privacy's Hybrid-Model
- A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation
- Mirror Learning: A Unifying Framework of Policy Optimisation
- Provably Adversarially Robust Nearest Prototype Classifiers
- Black-Box Tuning for Language-Model-as-a-Service
- NysADMM: faster composite convex optimization via low-rank approximation
- Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
- DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
- A Multi-objective / Multi-task Learning Framework Induced by Pareto Stationarity
- Analyzing and Mitigating Interference in Neural Architecture Search
- Robust Kernel Density Estimation with Median-of-Means principle
- Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
- Certifying Out-of-Domain Generalization for Blackbox Functions
- FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning
- Thompson Sampling for (Combinatorial) Pure Exploration
- Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
- Sparse Invariant Risk Minimization
- Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
- Calibrated Learning to Defer with One-vs-All Classifiers
- Intriguing Properties of Input-Dependent Randomized Smoothing
- Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
- Revisiting Online Submodular Minimization: Gap-Dependent Regret Bounds, Best of Both Worlds and Adversarial Robustness
- Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding
- Rotting Infinitely Many-Armed Bandits
- Learning Infinite-horizon Average-reward Markov Decision Process with Constraints
- Co-training Improves Prompt-based Learning for Large Language Models
- Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
- A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
- Directed Acyclic Transformer for Non-Autoregressive Machine Translation
- Forward Operator Estimation in Generative Models with Kernel Transfer Operators
- A Closer Look at Smoothness in Domain Adversarial Training
- DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks
- FriendlyCore: Practical Differentially Private Aggregation
- DNA: Domain Generalization with Diversified Neural Averaging
- Langevin Monte Carlo for Contextual Bandits
- Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
- StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
- Conditional GANs with Auxiliary Discriminative Classifier
- Balancing Discriminability and Transferability for Source-Free Domain Adaptation
- A deep convolutional neural network that is invariant to time rescaling
- ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder
- Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
- Prompting Decision Transformer for Few-Shot Policy Generalization
- On the Generalization Analysis of Adversarial Learning
- Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology
- Only tails matter: Average-Case Universality and Robustness in the Convex Regime
- Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent
- Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images
- Model Agnostic Sample Reweighting for Out-of-Distribution Learning
- LyaNet: A Lyapunov Framework for Training Neural ODEs
- Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
- DynaMixer: A Vision MLP Architecture with Dynamic Mixing
- Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
- Demystifying the Adversarial Robustness of Random Transformation Defenses
- Generative Cooperative Networks for Natural Language Generation
- Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity
- Consistent Polyhedral Surrogates for Top-k Classification and Variants
- Matching Normalizing Flows and Probability Paths on Manifolds
- Zero-shot AutoML with Pretrained Models
- Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
- Public Data-Assisted Mirror Descent for Private Model Training
- Channel Importance Matters in Few-Shot Image Classification
- Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
- Double Sampling Randomized Smoothing
- What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?
- Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets
- Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
- Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization
- Efficient Variance Reduction for Meta-learning
- On Collective Robustness of Bagging Against Data Poisoning
- Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions
- Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
- TPC: Transformation-Specific Smoothing for Point Cloud Models
- Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding
- Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time
- Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits
- Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
- Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder
- Hindering Adversarial Attacks with Implicit Neural Representations
- Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
- ROCK: Causal Inference Principles for Reasoning about Commonsense Causality
- Active Sampling for Min-Max Fairness
- Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback
- Region-Based Semantic Factorization in GANs
- Partial disentanglement for domain adaptation
- From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
- Online Continual Learning through Mutual Information Maximization
- Meaningfully debugging model mistakes using conceptual counterfactual explanations
- Robust Group Synchronization via Quadratic Programming
- An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees
- Additive Gaussian Processes Revisited
- pathGCN: Learning General Graph Spatial Operators from Paths
- Learning Iterative Reasoning through Energy Minimization
- Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
- UAST: Uncertainty-Aware Siamese Tracking
- Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data
- Probabilistic ODE Solutions in Millions of Dimensions
- Graph-Coupled Oscillator Networks
- DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
- Robust Counterfactual Explanations for Tree-Based Ensembles
- You Only Cut Once: Boosting Data Augmentation with a Single Cut
- Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding
- Adaptive Gaussian Process Change Point Detection
- HousE: Knowledge Graph Embedding with Householder Parameterization
- PoF: Post-Training of Feature Extractor for Improving Generalization
- A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions
- Generative Modeling for Multi-task Visual Learning
- Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
- Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
- Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
- Estimating and Penalizing Induced Preference Shifts in Recommender Systems
- HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
- Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances
- Meta-Learning Hypothesis Spaces for Sequential Decision-making
- Fenrir: Physics-Enhanced Regression for Initial Value Problems
- AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
- Learning to Hash Robustly, Guaranteed
- Stochastic Reweighted Gradient Descent
- ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
- Set Based Stochastic Subsampling
- Framework for Evaluating Faithfulness of Local Explanations
- Parametric Visual Program Induction with Function Modularization
- Residual-Based Sampling for Online Outlier-Robust PCA
- A Tighter Analysis of Spectral Clustering, and Beyond
- Variational nearest neighbor Gaussian process
- DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
- Policy Gradient Method For Robust Reinforcement Learning
- Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood
- G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters
- A Consistent and Efficient Evaluation Strategy for Attribution Methods
- Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times
- Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
- A query-optimal algorithm for finding counterfactuals
- Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
- SpeqNets: Sparsity-aware permutation-equivariant graph networks
- Streaming Algorithms for Support-Aware Histograms
- Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
- Linear Bandit Algorithms with Sublinear Time Complexity
- FedNL: Making Newton-Type Methods Applicable to Federated Learning
- Power-Law Escape Rate of SGD
- CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
- Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra
- Generalizing to New Physical Systems via Context-Informed Dynamics Model
- Variational Feature Pyramid Networks
- On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
- Spectral Representation of Robustness Measures for Optimization Under Input Uncertainty
- Self-conditioning Pre-Trained Language Models
- Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
- Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning
- Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
- Bayesian Optimization under Stochastic Delayed Feedback
- Position Prediction as an Effective Pretraining Strategy
- TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification
- XAI for Transformers: Better Explanations through Conservative Propagation
- VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
- Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
- Bayesian Optimization for Distributionally Robust Chance-constrained Problem
- Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization
- Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
- Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization
- Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
- Neural Implicit Dictionary Learning via Mixture-of-Expert Training
- Faster Algorithms for Learning Convex Functions
- Confidence Score for Source-Free Unsupervised Domain Adaptation
- Efficient Distributionally Robust Bayesian Optimization with Worst-case Sensitivity
- Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
- Correlated Quantization for Distributed Mean Estimation and Optimization
- Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems
- Deep and Flexible Graph Neural Architecture Search
- Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
- Interpretable Off-Policy Learning via Hyperbox Search
- Time Is MattEr: Temporal Self-supervision for Video Transformers
- Feature selection using e-values
- Gradient Based Clustering
- Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
- PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
- Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms
- Probabilistic Bilevel Coreset Selection
- GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
- Knowledge Base Question Answering by Case-based Reasoning over Subgraphs
- Neuron Dependency Graphs: A Causal Abstraction of Neural Networks
- Benchmarking and Analyzing Point Cloud Classification under Corruptions
- ActiveHedge: Hedge meets Active Learning
- Global Optimization of K-Center Clustering
- Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation
- Supervised Off-Policy Ranking
- Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms
- Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
- Large-Scale Graph Neural Architecture Search
- When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
- On the Adversarial Robustness of Causal Algorithmic Recourse
- Understanding The Robustness in Vision Transformers
- One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes
- Latent Outlier Exposure for Anomaly Detection with Contaminated Data
- The Primacy Bias in Deep Reinforcement Learning
- The Algebraic Path Problem for Graph Metrics
- On Implicit Bias in Overparameterized Bilevel Optimization
- Optimization-Induced Graph Implicit Nonlinear Diffusion
- Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
- Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm
- Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
- Steerable 3D Spherical Neurons
- Prototype Based Classification from Hierarchy to Fairness
- Coordinated Double Machine Learning
- Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations
- Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective
- Model-Free Opponent Shaping
- Modeling Irregular Time Series with Continuous Recurrent Units
- Neural-Symbolic Models for Logical Queries on Knowledge Graphs
- Exploiting Independent Instruments: Identification and Distribution Generalization
- On the Effects of Artificial Data Modification
- Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering
- Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
- TACTiS: Transformer-Attentional Copulas for Time Series
- Deep Probability Estimation
- Partial Counterfactual Identification from Observational and Experimental Data
- Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage
- Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\epsilon^{-7/4})$ Complexity
- Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
- CerDEQ: Certifiable Deep Equilibrium Model
- Uncertainty Modeling in Generative Compressed Sensing
- On Measuring Causal Contributions via do-interventions
- How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
- Understanding the unstable convergence of gradient descent
- Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
- Approximately Equivariant Networks for Imperfectly Symmetric Dynamics
- Going Deeper into Permutation-Sensitive Graph Neural Networks
- The Role of Deconfounding in Meta-learning
- Selective Network Linearization for Efficient Private Inference
- Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent
- Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass
- Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning
- Federated Minimax Optimization: Improved Convergence Analyses and Algorithms
- Simple and near-optimal algorithms for hidden stratification and multi-group learning
- Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
- IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data
- Learning from Counterfactual Links for Link Prediction
- CITRIS: Causal Identifiability from Temporal Intervened Sequences
- Efficient Computation of Higher-Order Subgraph Attribution via Message Passing
- The Teaching Dimension of Regularized Kernel Learners
- How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective
- Hessian-Free High-Resolution Nesterov Acceleration For Sampling
- Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm
- Being Properly Improper
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
- GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
- Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
- Online Balanced Experimental Design
- A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization
- Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation
- LSB: Local Self-Balancing MCMC in Discrete Spaces
- Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks
- Modular Conformal Calibration
- TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm
- A Langevin-like Sampler for Discrete Distributions
- On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions
- Multiclass learning with margin: exponential rates with no bias-variance trade-off
- Scalable Spike-and-Slab
- Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
- Describing Differences between Text Distributions with Natural Language
- AdaGrad Avoids Saddle Points
- Self-Organized Polynomial-Time Coordination Graphs
- Improving Language Models by Retrieving from Trillions of Tokens
- Principal Component Flows
- Causal structure-based root cause analysis of outliers
- Distinguishing rule- and exemplar-based generalization in learning systems
- Fast and Provable Nonconvex Tensor RPCA
- Individual Reward Assisted Multi-Agent Reinforcement Learning
- Closed-Form Diffeomorphic Transformations for Time Series Alignment
- Bit Prioritization in Variational Autoencoders via Progressive Coding
- Instrumental Variable Regression with Confounder Balancing
- Context-Aware Drift Detection
- Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning
- On Convergence of Gradient Descent Ascent: A Tight Local Analysis
- Generalized Beliefs for Cooperative AI
- Removing Batch Normalization Boosts Adversarial Training
- Generative Flow Networks for Discrete Probabilistic Modeling
- Causal Transformer for Estimating Counterfactual Outcomes
- Accelerating Shapley Explanation via Contributive Cooperator Selection
- High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails
- A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications
- Continual Repeated Annealed Flow Transport Monte Carlo
- Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness
- Minimax M-estimation under Adversarial Contamination
- Greedy when Sure and Conservative when Uncertain about the Opponents
- Forget-free Continual Learning with Winning Subnetworks
- Diffusion bridges vector quantized variational autoencoders
- Causal Inference Through the Structural Causal Marginal Problem
- An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
- An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn
- Minimizing Control for Credit Assignment with Strong Feedback
- Algorithms for the Communication of Samples
- A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
- Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
- Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
- FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
- Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
- Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
- DAVINZ: Data Valuation using Deep Neural Networks at Initialization
- Inductive Biases and Variable Creation in Self-Attention Mechanisms
- Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to Speech
- Low-Precision Stochastic Gradient Langevin Dynamics
- Anticorrelated Noise Injection for Improved Generalization
- Efficiently Learning the Topology and Behavior of a Networked Dynamical System Via Active Queries
- Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
- Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers
- Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
- Matching Learned Causal Effects of Neural Networks with Domain Priors
- Sample Efficient Learning of Predictors that Complement Humans
- Topology-aware Generalization of Decentralized SGD
- Towards Scaling Difference Target Propagation by Learning Backprop Targets
- Fast Relative Entropy Coding with A* coding
- Boosting Graph Structure Learning with Dummy Nodes
- Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games
- On the Practicality of Deterministic Epistemic Uncertainty
- Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
- Inferring Cause and Effect in the Presence of Heteroscedastic Noise
- Understanding Gradient Descent on the Edge of Stability in Deep Learning
- Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold
- Accurate Quantization of Measures via Interacting Particle-based Optimization
- Lazy Estimation of Variable Importance for Large Neural Networks
- Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis
- Combining Diverse Feature Priors
- Towards understanding how momentum improves generalization in deep learning
- Weisfeiler-Lehman Meets Gromov-Wasserstein
- Learning Domain Adaptive Object Detection with Probabilistic Teacher
- Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification
- Modeling Strong and Human-Like Gameplay with KL-Regularized Search
- On Numerical Integration in Neural Ordinary Differential Equations
- Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
- What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
- GenLabel: Mixup Relabeling using Generative Models
- Adaptive Data Analysis with Correlated Observations
- One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams
- Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
- Reverse Engineering the Neural Tangent Kernel
- Label-Free Explainability for Unsupervised Models
- Deep equilibrium networks are sensitive to initialization statistics
- When and How Mixup Improves Calibration
- Efficient PAC Learning from the Crowd with Pairwise Comparisons
- Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
- Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
- Principled Knowledge Extrapolation with GANs
- Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs
- Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework
- On Transportation of Mini-batches: A Hierarchical Approach
- On the Statistical Benefits of Curriculum Learning
- ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
- Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
- Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
- A Study of Face Obfuscation in ImageNet
- Stability Based Generalization Bounds for Exponential Family Langevin Dynamics
- VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
- Feature and Parameter Selection in Stochastic Linear Bandits
- Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics
- Surrogate Likelihoods for Variational Annealed Importance Sampling
- Generalized Data Distribution Iteration
- Data Augmentation as Feature Manipulation
- The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
- Fair Representation Learning through Implicit Path Alignment
- Fast Composite Optimization and Statistical Recovery in Federated Learning
- Local Augmentation for Graph Neural Networks
- Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features
- Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
- Bayesian Imitation Learning for End-to-End Mobile Manipulation
- Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
- Optimizing Tensor Network Contraction Using Reinforcement Learning
- Convolutional and Residual Networks Provably Contain Lottery Tickets
- Extracting Latent State Representations with Linear Dynamics from Rich Observations
- Mitigating Neural Network Overconfidence with Logit Normalization
- Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
- On Non-local Convergence Analysis of Deep Linear Networks
- A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling
- De novo mass spectrometry peptide sequencing with a transformer model
- Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows
- History Compression via Language Models in Reinforcement Learning
- Feature Learning and Signal Propagation in Deep Neural Networks
- For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria
- Learning fair representation with a parametric integral probability metric
- Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
- Variational Sparse Coding with Learned Thresholding
- Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
- Optimal Algorithms for Stochastic Multi-Level Compositional Optimization
- Structured Stochastic Gradient MCMC
- Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications
- Contextual Bandits with Large Action Spaces: Made Practical
- Diversified Adversarial Attacks based on Conjugate Gradient Method
- Rethinking Fano’s Inequality in Ensemble Learning
- Identifiability Conditions for Domain Adaptation
- Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance
- LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
- Understanding Contrastive Learning Requires Incorporating Inductive Biases
- Fair Generalized Linear Models with a Convex Penalty
- On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
- FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliers
- Streaming Algorithms for High-Dimensional Robust Statistics
- MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
- Efficient Learning for AlphaZero via Path Consistency
- Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
- Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
- HyperPrompt: Prompt-based Task-Conditioning of Transformers
- On the Equivalence Between Temporal and Static Equivariant Graph Representations
- Improving Mini-batch Optimal Transport via Partial Transportation
- Popular decision tree algorithms are provably noise tolerant
- Proximal Exploration for Model-guided Protein Sequence Design
- Variational Inference with Locally Enhanced Bounds for Hierarchical Models
- A data-driven approach for learning to control computers
- Deep Network Approximation in Terms of Intrinsic Parameters
- Learning to Infer Structures of Network Games
- Validating Causal Inference Methods
- Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert
- Robust Training under Label Noise by Over-parameterization
- Near-optimal rate of consistency for linear models with missing values
- Understanding and Improving Knowledge Graph Embedding for Entity Alignment
- Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval
- Centroid Approximation for Bootstrap: Improving Particle Quality at Inference
- Zero-Shot Reward Specification via Grounded Natural Language
- Coin Flipping Neural Networks
- Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
- The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks
- ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!
- Implicit Bias of the Step Size in Linear Diagonal Neural Networks
- Permutation Search of Tensor Network Structures via Local Sampling
- Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
- How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity
- Deep Reference Priors: What is the best way to pretrain a model?
- How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation
- Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
- Near-Optimal Learning of Extensive-Form Games with Imperfect Information
- Scalable Deep Gaussian Markov Random Fields for General Graphs
- Communication-Efficient Adaptive Federated Learning
- Extended Unconstrained Features Model for Exploring Deep Neural Collapse
- Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
- Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
- Examining Scaling and Transfer of Language Model Architectures for Machine Translation
- Model-Value Inconsistency as a Signal for Epistemic Uncertainty
- More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
- Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
- Anytime Information Cascade Popularity Prediction via Self-Exciting Processes
- RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
- Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems
- DNNR: Differential Nearest Neighbors Regression
- Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
- State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks
- Improving Policy Optimization with Generalist-Specialist Learning
- SE(3) Equivariant Graph Neural Networks with Complete Local Frames
- Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
- Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots
- From data to functa: Your data point is a function and you can treat it like one
- Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits
- MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution
- Decomposing Temporal High-Order Interactions via Latent ODEs
- Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning
- DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
- Generating Distributional Adversarial Examples to Evade Statistical Detectors
- DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
- On the Finite-Time Performance of the Knowledge Gradient Algorithm
- PINs: Progressive Implicit Networks for Multi-Scale Neural Representations
- Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
- Analysis of Stochastic Processes through Replay Buffers
- Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
- Improving Out-of-Distribution Robustness via Selective Augmentation
- Differentiable Top-k Classification Learning
- Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
- Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
- DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
- Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning
- RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval
- Modeling Adversarial Noise for Adversarial Training
- Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
- Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
- Generative Coarse-Graining of Molecular Conformations
- End-to-End Balancing for Causal Continuous Treatment-Effect Estimation
- Communicating via Markov Decision Processes
- Modeling Structure with Undirected Neural Networks
- Improving Adversarial Robustness via Mutual Information Estimation
- Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks
- No-Regret Learning in Time-Varying Zero-Sum Games
- LIMO: Latent Inceptionism for Targeted Molecule Generation
- Role-based Multiplex Network Embedding
- Approximate Bayesian Computation with Domain Expert in the Loop
- PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
- QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning
- Certified Neural Network Watermarks with Randomized Smoothing
- FOCUS: Familiar Objects in Common and Uncommon Settings
- A Resilient Distributed Boosting Algorithm
- Training Your Sparse Neural Network Better with Any Mask
- Achieving Minimax Rates in Pool-Based Batch Active Learning
- Learning to Separate Voices by Spatial Regions
- Measure Estimation in the Barycentric Coding Model
- Discrete Probabilistic Inverse Optimal Transport
- DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
- Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
- Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
- Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
- Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards
- Federated Learning with Positive and Unlabeled Data
- Active Multi-Task Representation Learning
- Easy Variational Inference for Categorical Models via an Independent Binary Approximation
- Sanity Simulations for Saliency Methods
- Adversarial Vulnerability of Randomized Ensembles
- Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing
- On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation
- Streaming Inference for Infinite Feature Models
- Out-of-Distribution Detection with Deep Nearest Neighbors
- Congested Bandits: Optimal Routing via Short-term Resets
- Optimizing Sequential Experimental Design with Deep Reinforcement Learning
- Differentially Private Maximal Information Coefficients
- Stochastic Rising Bandits
- 3D Infomax improves GNNs for Molecular Property Prediction
- Counterfactual Transportability: A Formal Approach
- A Temporal-Difference Approach to Policy Gradient Estimation
- Sparse Double Descent: Where Network Pruning Aggravates Overfitting
- Metric-Fair Active Learning
- Biological Sequence Design with GFlowNets
- Identification of Linear Non-Gaussian Latent Hierarchical Structure
- MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
- The CLRS Algorithmic Reasoning Benchmark
- Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
- Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
- Metric-Fair Classifier Derandomization
- Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
- COAT: Measuring Object Compositionality in Emergent Representations
- Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
- Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
- Neurotoxin: Durable Backdoors in Federated Learning
- Revisiting Consistency Regularization for Deep Partial Label Learning
- Interactively Learning Preference Constraints in Linear Bandits
- Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer
- Generalization and Robustness Implications in Object-Centric Learning
- Variational Inference for Infinitely Deep Neural Networks
- Actor-Critic based Improper Reinforcement Learning
- On the Difficulty of Defending Self-Supervised Learning against Model Extraction
- Understanding Robust Generalization in Learning Regular Languages
- Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
- Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
- Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification
- Convergence of Uncertainty Sampling for Active Learning
- Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
- NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning
- Personalized Federated Learning via Variational Bayesian Inference
- On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs
- Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
- Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
- Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching
- PDE-Based Optimal Strategy for Unconstrained Online Learning
- A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks
- Thompson Sampling for Robust Transfer in Multi-Task Bandits
- Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules
- Action-Sufficient State Representation Learning for Control with Structural Constraints
- Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
- The Geometry of Robust Value Functions
- Certified Adversarial Robustness Under the Bounded Support Set
- AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems
- Fast Lossless Neural Compression with Integer-Only Discrete Flows
- Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
- PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information
- Constants Matter: The Performance Gains of Active Learning
- EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
- Bayesian Deep Embedding Topic Meta-Learner
- Denoised MDPs: Learning World Models Better Than the World Itself
- Predicting Out-of-Distribution Error with the Projection Norm
- A Modern Self-Referential Weight Matrix That Learns to Modify Itself
- SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
- On Learning Mixture of Linear Regressions in the Non-Realizable Setting
- Multicoated Supermasks Enhance Hidden Networks
- Cross-Space Active Learning on Graph Convolutional Networks
- Efficient Approximate Inference for Stationary Kernel on Frequency Domain
- Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
- Short-Term Plasticity Neurons Learning to Learn and Forget
- SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
- Random Forest Density Estimation
- $p$-Laplacian Based Graph Neural Networks
- The dynamics of representation learning in shallow, non-linear autoencoders
- SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
- Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
- The Infinite Contextual Graph Markov Model
- Improved Regret for Differentially Private Exploration in Linear MDP
- Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization
- A New Perspective on the Effects of Spectrum in Graph Neural Networks
- Gradient Descent on Neurons and its Link to Approximate Second-order Optimization
- NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks
- Equivariant Quantum Graph Circuits
- Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks
- Matching Structure for Dual Learning
- Bayesian Nonparametrics for Offline Skill Discovery
- RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
- Differentially Private Community Detection for Stochastic Block Models
- Implicit Bias of Linear Equivariant Networks
- Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks
- A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
- Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
- A Theoretical Comparison of Graph Neural Network Extensions
- Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime
- Detached Error Feedback for Distributed SGD with Random Sparsification
- Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
- The State of Sparse Training in Deep Reinforcement Learning
- Partial Label Learning via Label Influence Function
- Efficient Online ML API Selection for Multi-Label Classification Tasks
- Auxiliary Learning with Joint Task and Data Scheduling
- Variational On-the-Fly Personalization
- Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data
- YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone
- Curriculum Reinforcement Learning via Constrained Optimal Transport
- Training OOD Detectors in their Natural Habitats
- Hermite Polynomial Features for Private Data Generation
- Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
- Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees
- Entropic Causal Inference: Graph Identifiability
- Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
- Deep symbolic regression for recurrence prediction
- Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
- Inducing Causal Structure for Interpretable Neural Networks
- Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
- Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
- How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
- Datamodels: Understanding Predictions with Data and Data with Predictions
- Understanding Robust Overfitting of Adversarial Training and Beyond
- Architecture Agnostic Federated Learning for Neural Networks
- Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
- Geometric Multimodal Contrastive Representation Learning
- Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
- SDQ: Stochastic Differentiable Quantization with Mixed Precision
- Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning
- Neural Tangent Kernel Empowered Federated Learning
- Deduplicating Training Data Mitigates Privacy Risks in Language Models
- Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
- A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources
- Conformal Prediction Sets with Limited False Positives
- Generalizing Gaussian Smoothing for Random Search
- Universality of Winning Tickets: A Renormalization Group Perspective
- Bounding the Width of Neural Networks via Coupled Initialization - A Worst Case Analysis
- IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
- Constrained Offline Policy Optimization
- Probabilistically Robust Learning: Balancing Average- and Worst-case Performance
- Private frequency estimation via projective geometry
- Deep Causal Metric Learning
- Scalable Computation of Causal Bounds
- Supervised Learning with General Risk Functionals
- Constrained Discrete Black-Box Optimization using Mixed-Integer Programming
- Loss Function Learning for Domain Generalization by Implicit Gradient
- The Neural Race Reduction: Dynamics of Abstraction in Gated Networks
- Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
- Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
- Feature Space Particle Inference for Neural Network Ensembles
- Faster Privacy Accounting via Evolving Discretization
- Learning Symmetric Embeddings for Equivariant World Models
- Locally Sparse Neural Networks for Tabular Biomedical Data
- Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
- Risk-Averse No-Regret Learning in Online Convex Games
- GraphFM: Improving Large-Scale GNN Training via Feature Momentum
- Efficient Learning of CNNs using Patch Based Features
- Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation
- Reinforcement Learning with Action-Free Pre-Training from Videos
- A Study on the Ramanujan Graph Property of Winning Lottery Tickets
- The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
- Accelerated Federated Learning with Decoupled Adaptive Optimization
- Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification
- A Statistical Manifold Framework for Point Cloud Data
- Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters
- Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
- Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
- Symmetric Machine Theory of Mind
- Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
- PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
- Private Adaptive Optimization with Side information
- Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums
- Detecting Corrupted Labels Without Training a Model to Predict
- HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
- Robust Multi-Objective Bayesian Optimization Under Input Noise
- A Differential Entropy Estimator for Training Neural Networks
- Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
- PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance
- Delayed Reinforcement Learning by Imitation
- EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning
- Secure Quantized Training for Deep Learning
- TSPipe: Learn from Teacher Faster with Pipelines
- Prototype-Anchored Learning for Learning with Imperfect Annotations
- A Natural Actor-Critic Framework for Zero-Sum Markov Games
- Gradient-Free Method for Heavily Constrained Nonconvex Optimization
- Scaling Out-of-Distribution Detection for Real-World Settings
- Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
- LCANets: Lateral Competition Improves Robustness Against Corruption and Attack
- Reachability Constrained Reinforcement Learning
- Fisher SAM: Information Geometry and Sharpness Aware Minimisation
- Private optimization in the interpolation regime: faster rates and hardness results
- Personalized Federated Learning through Local Memorization
- Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters
- Distributionally Robust $Q$-Learning
- Sequential- and Parallel- Constrained Max-value Entropy Search via Information Lower Bound
- Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations
- Non-Vacuous Generalisation Bounds for Shallow Neural Networks
- Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series
- Adaptive Model Design for Markov Decision Process
- Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
- Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
- Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points
- Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm
- Sparsity in Partially Controllable Linear Systems
- The power of first-order smooth optimization for black-box non-smooth problems
- SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
- Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
- Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
- Goal Misgeneralization in Deep Reinforcement Learning
- Towards Understanding Sharpness-Aware Minimization
- Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making
- Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
- Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
- Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots
- Does the Data Induce Capacity Control in Deep Learning?
- Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation
- A Neural Tangent Kernel Perspective of GANs
- Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
- Adapting k-means Algorithms for Outliers
- Equivariance versus Augmentation for Spherical Images
- Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness
- Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
- Composing Partial Differential Equations with Physics-Aware Neural Networks
- Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
- Invariant Ancestry Search
- Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization
- Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
- Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
- Memory-Based Model Editing at Scale
- Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
- Neural Inverse Transform Sampler
- Unaligned Supervision for Automatic Music Transcription in The Wild
- Online Algorithms with Multiple Predictions
- Neural Network Poisson Models for Behavioural and Neural Spike Train Data
- Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning
- Winning the Lottery Ahead of Time: Efficient Early Network Pruning
- Towards Coherent and Consistent Use of Entities in Narrative Generation
- Antibody-Antigen Docking and Design via Hierarchical Structure Refinement
- Fourier Learning with Cyclical Data
- Parsimonious Learning-Augmented Caching
- A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks
- Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
- Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
- Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more
- Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
- Continuous Control with Action Quantization from Demonstrations
- Diffusion Models for Adversarial Purification
- Entropic Gromov-Wasserstein between Gaussian Distributions
- Linear Adversarial Concept Erasure
- RUMs from Head-to-Head Contests
- GACT: Activation Compressed Training for Generic Network Architectures
- A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs
- AutoSNN: Towards Energy-Efficient Spiking Neural Networks
- Shuffle Private Linear Contextual Bandits
- Optimally Controllable Perceptual Lossy Compression
- Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
- Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
- No-Regret Learning in Partially-Informed Auctions
- Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features
- Fast Finite Width Neural Tangent Kernel
- Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
- Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Learning to Solve PDE-constrained Inverse Problems with Graph Networks
- Inverse Contextual Bandits: Learning How Behavior Evolves over Time
- VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis
- On Last-Iterate Convergence Beyond Zero-Sum Games
- Robustness in Multi-Objective Submodular Optimization: a Quantile Approach
- Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes
- Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning
- Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
- Towards Uniformly Superhuman Autonomy via Subdominance Minimization
- Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games
- Provable Domain Generalization via Invariant-Feature Subspace Recovery
- Dataset Condensation via Efficient Synthetic-Data Parameterization
- Subspace Learning for Effective Meta-Learning
- Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
- Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
- Searching for BurgerFormer with Micro-Meso-Macro Space Design
- Learning to Estimate and Refine Fluid Motion with Physical Dynamics
- Unsupervised Image Representation Learning with Deep Latent Particles
- Continual Learning via Sequential Function-Space Variational Inference
- COLA: Consistent Learning with Opponent-Learning Awareness
- Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
- Functional Output Regression with Infimal Convolution: Exploring the Huber and $\epsilon$-insensitive Losses
- Multi-scale Feature Learning Dynamics: Insights for Double Descent
- Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
- Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
- Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks
- Efficient Test-Time Model Adaptation without Forgetting
- A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
- Continual Learning with Guarantees via Weight Interval Constraints
- Measuring dissimilarity with diffeomorphism invariance
- Dataset Condensation with Contrastive Signals
- A Simple Unified Framework for High Dimensional Bandit Problems
- An Intriguing Property of Geophysics Inversion
- Interactive Inverse Reinforcement Learning for Cooperative Games
- Neuro-Symbolic Hierarchical Rule Induction
- Nested Bandits
- Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications
- A Framework for Learning to Request Rich and Contextually Useful Information from Humans
- Faster Fundamental Graph Algorithms via Learned Predictions
- Importance Weighted Kernel Bayes' Rule
- Equivariant Priors for compressed sensing with unknown orientation
- A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds
- Particle Transformer for Jet Tagging
- A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
- General-purpose, long-context autoregressive modeling with Perceiver AR
- Information Discrepancy in Strategic Learning
- Input Dependent Sparse Gaussian Processes
- Learning Stochastic Shortest Path with Linear Function Approximation
- Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering
- An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
- Injecting Logical Constraints into Neural Networks via Straight-Through Estimators
- Branching Reinforcement Learning
- BabelTower: Learning to Auto-parallelized Program Translation
- Robust Imitation Learning against Variations in Environment Dynamics
- Marginal Tail-Adaptive Normalizing Flows
- A Psychological Theory of Explainability
- AutoIP: A United Framework to Integrate Physics into Gaussian Processes
- Difference Advantage Estimation for Multi-Agent Policy Gradients
- Fair and Fast k-Center Clustering for Data Summarization
- Nyström Kernel Mean Embeddings
- Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
- Fast rates for noisy interpolation require rethinking the effect of inductive bias
- ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
- Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
- Task-aware Privacy Preservation for Multi-dimensional Data
- Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
- Online and Consistent Correlation Clustering
- Distribution Regression with Sliced Wasserstein Kernels
- Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path
- On Distribution Shift in Learning-based Bug Detectors
- Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation
- NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
- Strategic Representation
- Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
- Generalized Leverage Scores: Geometric Interpretation and Applications
- Adversarial Masking for Self-Supervised Learning
- Ripple Attention for Visual Perception with Sub-quadratic Complexity
- A Context-Integrated Transformer-Based Neural Network for Auction Design
- Learning Stable Classifiers by Transferring Unstable Features
- Dynamic Topic Models for Temporal Document Networks
- Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
- Self-supervised Models are Good Teaching Assistants for Vision Transformers
- Domain Adaptation for Time Series Forecasting via Attention Sharing
- Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
- A Functional Information Perspective on Model Interpretation
- OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
- Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
- Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
- Attentional Meta-learners for Few-shot Polythetic Classification
- Be Like Water: Adaptive Floating Point for Machine Learning
- Multirate Training of Neural Networks
- In defense of dual-encoders for neural ranking
- Disentangling Disease-related Representation from Obscure for Disease Prediction
- C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebra
- Lie Point Symmetry Data Augmentation for Neural PDE Solvers
- Variational Wasserstein gradient flow
- Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints
- From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers
- Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
- Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning
- Nonlinear Feature Diffusion on Hypergraphs
- Fast Provably Robust Decision Trees and Boosting
- Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition
- Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
- Offline Meta-Reinforcement Learning with Online Self-Supervision
- Building Robust Ensembles via Margin Boosting
- A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving
- Linear Complexity Randomized Self-attention Mechanism
- Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning
- A Simple Reward-free Approach to Constrained Reinforcement Learning
- Kernel Methods for Radial Transformed Compositional Data with Many Zeros
- Order Constraints in Optimal Transport
- Nonparametric Embeddings of Sparse High-Order Interaction Events
- Adaptive Second Order Coresets for Data-efficient Machine Learning
- Divergence-Regularized Multi-Agent Actor-Critic
- Investigating Generalization by Controlling Normalized Margin
- Exact Learning of Preference Structure: Single-peaked Preferences and Beyond
- Efficient Representation Learning via Adaptive Context Pooling
- Learning of Cluster-based Feature Importance for Electronic Health Record Time-series
- Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
- Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning
- Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
- Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
- Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach
- Selling Data To a Machine Learner: Pricing via Costly Signaling
- Temporal Difference Learning for Model Predictive Control
- NOMU: Neural Optimization-based Model Uncertainty
- Efficient Low Rank Convex Bounds for Pairwise Discrete Graphical Models
- Off-Policy Reinforcement Learning with Delayed Rewards
- Hardness and Algorithms for Robust and Sparse Optimization
- Model Selection in Batch Policy Optimization
- Direct Behavior Specification via Constrained Reinforcement Learning
- PAC-Bayesian Bounds on Rate-Efficient Classifiers
- VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training
- Fast Population-Based Reinforcement Learning on a Single Machine
- Adaptive Conformal Predictions for Time Series
- Fairness with Adaptive Weights
- More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees
- Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
- NeuralEF: Deconstructing Kernels by Deep Neural Networks
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
- Understanding Instance-Level Impact of Fairness Constraints
- Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning
- Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning
- The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
- Graph Neural Architecture Search Under Distribution Shifts
- Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
- Visual Attention Emerges from Recurrent Sparse Reconstruction
- Rethinking Graph Neural Networks for Anomaly Detection
- Optimal Estimation of Policy Gradient via Double Fitted Iteration
- Achieving Fairness at No Utility Cost via Data Reweighing with Influence
- On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum
- Wide Neural Networks Forget Less Catastrophically
- Instance Dependent Regret Analysis of Kernelized Bandits
- Evolving Curricula with Regret-Based Environment Design
- How Powerful are Spectral Graph Neural Networks
- Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis
- Transformer Quality in Linear Time
- Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models
- Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
- Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model
- SPDY: Accurate Pruning with Speedup Guarantees
- A Unified View on PAC-Bayes Bounds for Meta-Learning
- EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
- Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
- Constraint-based graph network simulator
- The Complexity of k-Means Clustering when Little is Known
- What Dense Graph Do You Need for Self-Attention?
- Proving Theorems using Incremental Learning and Hindsight Experience Replay
- Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
- Selective Regression under Fairness Criteria
- Flashlight: Enabling Innovation in Tools for Machine Learning
- MAML and ANIL Provably Learn Representations
- Tell me why! Explanations support learning relational and causal structure
- Transformers are Meta-Reinforcement Learners
- PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs
- Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime
- Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images
- Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
- Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
- Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
- On the Robustness of CountSketch to Adaptive Inputs
- C-MinHash: Improving Minwise Hashing with Circulant Permutation
- Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
- Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
- Structure-Aware Transformer for Graph Representation Learning
- 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
- Multi Resolution Analysis (MRA) for Approximate Self-Attention
- Neural Inverse Kinematic
- On the Role of Discount Factor in Offline Reinforcement Learning
- Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization
- Constrained Variational Policy Optimization for Safe Reinforcement Learning
- Bregman Neural Networks
- Nearly Optimal Catoni’s M-estimator for Infinite Variance
- Convergence of Invariant Graph Networks
- GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
- Revisiting End-to-End Speech-to-Text Translation From Scratch
- Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning
- Global Optimization Networks
- ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
- Quantifying and Learning Linear Symmetry-Based Disentanglement
- Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
- Rich Feature Construction for the Optimization-Generalization Dilemma
- Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
- Data Scaling Laws in NMT: The Effect of Noise and Architecture
- A Regret Minimization Approach to Multi-Agent Control
- Generalized Federated Learning via Sharpness Aware Minimization
- Federated Learning with Label Distribution Skew via Logits Calibration
- Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
- Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis
- NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
- Object Permanence Emerges in a Random Walk along Memory
- Dialog Inpainting: Turning Documents into Dialogs
- Multi-slots Online Matching with High Entropy
- Delay-Adaptive Step-sizes for Asynchronous Learning
- Adaptive Random Walk Gradient Descent for Decentralized Optimization
- PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
- Contextual Information-Directed Sampling
- Resilient and Communication Efficient Learning for Heterogeneous Federated Systems
- Flow-Guided Sparse Transformer for Video Deblurring
- Safe Exploration for Efficient Policy Evaluation and Comparison
- Decision-Focused Learning: Through the Lens of Learning to Rank
- FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
- POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
- Utilizing Expert Features for Contrastive Learning of Time-Series Representations
- Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
- Augment with Care: Contrastive Learning for Combinatorial Problems
- N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations
- Adversarial Attacks on Gaussian Process Bandits
- On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
- Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
- Learning Augmented Binary Search Trees
- Improving Screening Processes via Calibrated Subset Selection
- Secure Distributed Training at Scale
- (Non-)Convergence Results for Predictive Coding Networks
- Universal and data-adaptive algorithms for model selection in linear contextual bandits
- Cycle Representation Learning for Inductive Relation Prediction
- Staged Training for Transformer Language Models
- GALAXY: Graph-based Active Learning at the Extreme
- Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language
- EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
- Communication-efficient Distributed Learning for Large Batch Optimization
- On the Convergence of the Shapley Value in Parametric Bayesian Learning Games
- ASAP.SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD
- Representation Topology Divergence: A Method for Comparing Neural Network Representations.
- Regret Minimization with Performative Feedback
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
- When Are Linear Stochastic Bandits Attackable?
- Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
- Imitation Learning by Estimating Expertise of Demonstrators
- Data-SUITE: Data-centric identification of in-distribution incongruous examples
- Counterfactual Prediction for Outcome-Oriented Treatments
- Off-Policy Evaluation for Large Action Spaces via Embeddings
- Self-supervised learning with random-projection quantizer for speech recognition
- A Simple Guard for Learned Optimizers
- Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning
- The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention
- Deep Hierarchy in Bandits
- MetAug: Contrastive Learning via Meta Feature Augmentation
- Learning Multiscale Transformer Models for Sequence Generation
- Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds
- Making Linear MDPs Practical via Contrastive Representation Learning
- An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming
- Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach
- Flowformer: Linearizing Transformers with Conservation Flows
- Distributionally-Aware Kernelized Bandit Problems for Risk Aversion
- Investigating Why Contrastive Learning Benefits Robustness against Label Noise
- NP-Match: When Neural Processes meet Semi-Supervised Learning
- Interactive Correlation Clustering with Existential Cluster Constraints
- Flow-based Recurrent Belief State Learning for POMDPs
- Multi-Level Branched Regularization for Federated Learning
- Least Squares Estimation using Sketched Data with Heteroskedastic Errors
- Sketching Algorithms and Lower Bounds for Ridge Regression
- Spatial-Channel Token Distillation for Vision MLPs
- Asymptotically-Optimal Gaussian Bandits with Side Observations
- Contrastive Learning with Boosted Memorization
- Proximal and Federated Random Reshuffling
- Simultaneous Graph Signal Clustering and Graph Learning
- A Parametric Class of Approximate Gradient Updates for Policy Optimization
- Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
- Revisiting the Effects of Stochasticity for Hamiltonian Samplers
- Debiaser Beware: Pitfalls of Centering Regularized Transport Maps
- On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
- Neurocoder: General-Purpose Computation Using Stored Neural Programs
- Learning from a Learning User for Optimal Recommendations
- Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
- Federated Learning with Partial Model Personalization
- Bregman Power k-Means for Clustering Exponential Family Data
- Retrieval-Augmented Reinforcement Learning
- How to Leverage Unlabeled Data in Offline Reinforcement Learning
- Scaling Structured Inference with Randomization
- Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes
- Utility Theory for Sequential Decision Making
- Improving Transformers with Probabilistic Attention Keys
- Thresholded Lasso Bandit
- Interventional Contrastive Learning with Meta Semantic Regularizer
- A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms
- SpaceMAP: Visualizing High-Dimensional Data by Space Expansion
- Robust Policy Learning over Multiple Uncertainty Sets
- Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
- Discrete Tree Flows via Tree-Structured Permutations
- Active Nearest Neighbor Regression Through Delaunay Refinement
- Online Learning with Knapsacks: the Best of Both Worlds
- Rethinking Attention-Model Explainability through Faithfulness Violation Test
- Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences
- On the Surrogate Gap between Contrastive and Supervised Losses
- Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology
- Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors
- Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
- Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
- Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation
- A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1
- Optimal Clustering with Noisy Queries via Multi-Armed Bandit
- AGNAS: Attention-Guided Micro- and Macro-Architecture Search
- Decentralized Online Convex Optimization in Networked Systems
- Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning
- Iterative Double Sketching for Faster Least-Squares Optimization
- Understanding Doubly Stochastic Clustering
- Learning Dynamics and Generalization in Deep Reinforcement Learning
- Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
- RITA: a Study on Scaling Up Generative Protein Sequence Models
- Learning Batch-Invariant Representations with Domain Adaptation in Large Scale Proteomics Data
- COEM: Cross-Modal Embedding for MetaCell Identification
- Does Continual Learning Equally Forget All Parameters?
- PA-GNN: Parameter-Adaptive Graph Neural Networks
- Triangular Dropout: Variable Network Width without Retraining
- EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
- Learning to rank metabolites across datasets
- A Theoretical View on Sparsely Activated Networks
- 7-UP: generating in silico CODEX from a small set of immunofluorescence markers
- RTfold: RNA secondary structure prediction using deep learning with domain inductive bias
- A Deep Learning Framework for Estimating Cell-specific Kinetic Rates of RNA Velocity
- A High Fidelity Cybersecurity Dataset for Attack Modeling
- Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
- Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems
- Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
- ACD-G: Enhancing Autonomous Cyber Defence Agent Generalisation Through Graph Embedded Network Representation
- Hypergraph Topological Features for Autoencoder-Based Intrusion Detection for Cybersecurity Data
- Exploiting and Defending Against the Approximate Linearity of Apple’s NeuralHash
- Reducing Exploitability with Population Based Training
- Using Machine Learning to Infer Plausible and Undetected Cyber Threat, Vulnerability and Mitigation Relationships
- An Artificial Intelligence-Enabled Framework for Optimizing the Dynamic Cyber Vulnerability Management Process
- Probabilistic basis decomposition for characterizing temporal dynamics of gene expression
- SNVformer: An Attention-based Deep Neural Network for GWAS Data
- Extracting Part of Signal Representation from Direct RNA Squiggle for Modification Detection
- A mechanistic probabilistic model of genomic compartments
- TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-binding analyses
- Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions
- Assessing the utility of genomic deep learning models for disease-relevant variant effect prediction
- Molecular Fingerprints Are a Simple Yet Effective Solution to the Drug–Drug Interaction Problem
- Supernet Training for Federated Image Classification
- Achieving High TinyML Accuracy through Selective Cloud Interactions
- Slimmable Quantum Federated Learning
- Sparse Relational Reasoning with Object-centric Representations
- Play It Cool: Dynamic Shifting Prevents Thermal Throttling
- Efficient Sparsely Activated Transformers
- The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts
- Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction
- Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression
- Synthesizing Personalized Non-speech Vocalization from Discrete Speech Representations
- Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms
- Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression
- Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers
- Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizations
- Self-supervision and Learnable STRFs for Age, Emotion and Country Prediction
- Comparing supervised and self-supervised embedding for ExVo Multi-Task learning track
- Burst2Vec: An Adversarial Multi-Task Approach for Predicting Emotion, Age, and Origin from Vocal Bursts
- Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
- Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models
- When Neural ODE Meets Adaptive Moment Estimation: Boosting Efficiency, Stability and Accuracy of Neural ODEs Together
- Continuous Methods : Hamiltonian Domain Translation
- Continuous Methods : Adaptively intrusive reduced order model closure
- Temporal Graph Neural Networks with Time-Continuous Latent States
- Epsilon-Greedy Reinforcement Learning Policy in Continuous-Time Systems
- Modeling Solutions to Ordinary and Partial Differential Equations with Continuous Initial Value Networks
- Recovering Stochastic Dynamics via Gaussian Schrödinger Bridges
- Gradient Flows for L2 Support Vector Machine Training
- Non-convex online learning via algorithmic equivalence
- Faster Training of Neural ODEs Using Gauß–Legendre Quadrature
- Accelerated Methods for Distributed Optimization Problems using Fixed-time Stability of Continuous-time Dynamical Systems
- Everyone Matters: Customizing the Dynamics of Decision Boundary for Adversarial Robustness
- A Multistep Frank-Wolfe Method
- Contrasting Discrete and Continuous Time Methods for Bayesian System Identification
- Markovian Gaussian Process Autoencoders
- Should You Follow the Gradient Flow? Insights from Runge-Kutta Gradient Descent
- Identification of Hidden Clusters of Time Series with Hybrid Neural Networks Integrating Expert Models
- Connections between Kernel Analog Forecasting and Gaussian Process Regression
- Data Assimilation and Neural ODEs for learning latent dynamics
- Riemannian Diffusion Schr\"odinger Bridge
- Physics-Informed Neural Operator for Learning Partial Differential Equations
- MQTransformer: Context Dependent Attention and Bregman Volatility
- Continuous-time Analysis for Variational Inequalities: An Overview & Desiderata
- Estimating Treatment Effects in Continuous Time with Hidden Confounders
- Principle of Least Action Approach to Accelerate Neural Ordinary Differential Equations
- The Gap Between Continuous and Discrete Gradient Descent
- Learning to Discretize for Continuous-time Sequence Compression
- Towards a General Purpose CNN for Long Range Dependencies in $N$D
- A New Look on Diffusion Times for Score-based Generative Models
- Adaptive Interest for Emphatic Reinforcement Learning
- Discovered Policy Optimisation
Spotlight (Contributed)s
- Generating Diverse Cooperative Agents by Learning Incompatible Policies
- High Performance Simulation for Scalable Multi-Agent Reinforcement Learning
- Calibrating Agent-based Models to Microdata with Graph Neural Networks
- The StarCraft Multi-Agent Challenges+ : Learning of Sub-tasks and Environmental Benefits without Precise Reward Functions
Spotlight Presentations
Spotlight Talks
- Graduate School Fellowship Professional Tips
- Patent Process
- Query Release via the Johnson Lindenstrauss Lemma
- Paper 23: Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving
- Visualizing Privacy-Utility Trade-Offs in Differentially Private Data Releases
- Paper 15: On the Robustness of Safe Reinforcement Learning under Observational Perturbations
- Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It
- Private Convex Optimization via Exponential Mechanism
- The Price of Differential Privacy under Continual Observation
- Unlocking High-Accuracy Differentially Private Image Classification through Scale
Spotlights
Stage Program Concludes
Talks
- Frank Noe
- Rafael Gomez-Bombarelli
- Daphne Koller
- Animashree Anandkumar
- Anthony Gitter
- Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training
- Jiequn Han
- Carla P. Gomes
- Max Tegmark
- An Introduction to Quantum Natural Language Processing and a Study Case
- Bottleneck-based Encoder-decoder ARchitecture (BEAR) for Learning Unbiased Consumer-to-Consumer Image Representations
- Opening remarks
- Introduction and Background
- Classifier Guided Diffusion for Image Inpainting: Applications to Fine Art
- Introduction
- A Model-Based Filter to Improve Local Differential Privacy
- Mathematical Background: Linear Mixed Effects Model (LMEM) and Generalized Likelihood Ratio Test (GLRT)
- Deep Learning for Causality
- Significance
- Reliability
- Causality for Deep Learning
- Recap: A worked-through example
- A Study on the Predictability of Sample Learning Consistency
- Link Prediction from Heterogeneous Opinion Mining Networks with Multi-Domain Applications
- Mathematical background: Generalized Additive Model (GAM)
- Validity
- Transfer Learning with Joint Fine-Tuning for Multimodal Sentiment Analysis
- Closing remarks
- Selected Paper #1 - FedControl: When Control Theory Meets Federated Learning
- Selected Paper #2 - Test-Time Adaptation with Principal Component Analysis
- Selected Paper #3 - Light Weight Character and Shape Recognition for Autonomous Drones
- Selected Paper #4 - A Compact Transformer-based Classifier with Selected Hybrid Features from Different Patch Sequences for Image Classification
- Selected Paper #5 - An Efficient Modern Baseline for FloodNet VQA
- Selected Paper #6 - Generating Synthetic Population
- Learning objectives and preferences: WHAT DATA? From diverse types of human data
- Learning objectives and preferences: HOW? Actively
- Learning to interact: GAME! Coordinating actions with humans via game theory
- Learning to interact: PARTIAL OBSERVABILITY The actions you take as part of the task are the queries!
- Learning to interact: PARTIAL OBSERVABILITY + GAME Theory of mind on steroids
- Learning to interact: LET’S LEARN IT ALL Implicit coordination though learned representations
- Opening Remarks
- Trends Driving Big Models
- New Views of ML parallelism: Intra- and Inter-Operator Parallelism
- Inter-Operator Parallelism
- Intra-Operator Parallelism
- Auto Parallelization of ML Computation
- Tools for Big Model, Key Takeaways, and Q&A
- Opening remarks
- Sebastian Riedel
- Adversarial attacks on deep learning : Model explanation & transfer to the physical world
- Invited Speaker: Ivan Istomin
- Invited Talk 1 (Gagandeep Singh): Proof Sharing and Transfer for Boosting Neural Network Verification
- Invited Speaker: David Held
- Introduction and opening remarks
- Invited Talk 1: Aleksander Mądry
- Nils Reimers
- Invited Talk: Melanie Zeilinger
- A tale of adversarial attacks & out-of-distribution detection stories in the activation space
- Characterizing Neural Network Verification for Systems with NN4SysBench
- Machine Learning Security: Lessons Learned and Future Challenges
- Invited Talk 2 (Anton Dahbura): Undeterminism and the AI Uncertainty Principle
- John Schulman
- Invited Talk 2: Lucas Beyer
- Invited Talk 3 (M. Pawan Kumar): Neural Networks for Neural Network Verification
- Paper 16: Constrained Model-based Reinforcement Learning via Robust Planning
- What Can the Primate Brain Teach Us about Robust Object Recognition?
- Paper 12: SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
- Paper 11: Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space
- Invited Talk 3: Chelsea Finn
- Autonomous Racing Virtual Challenge: Contributed Talks
- Paper 14: The Edge of Disaster: A Battle Between Autonomous Racing and Safety
- New adversarial ML applications on safety-critical human-robot systems
- Invited Talk 4: Alexei Efros
- Jimmy Lin
- Dr. Aleksander Madry's Talk
- Invited Talk 4 (Suman Jana): Efficient Neural Network Verification using Branch and Bound
- Invited Speaker: Peter Stone
- Spotlight Talks
- Invited Talk 5 (Somayeh Sojoudi): Computational Methods for Non-convex Machine Learning Problems
- Ellie Pavlick
- Invited Speaker: Todd Hester
- IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
- Robust physical perturbation attacks and defenses for deep learning visual classifiers
- Contributed Talk 1: Dialog Inpainting: Turning Documents into Dialogs
- Contributed Talk 2: Huge Frozen Language Models as Readers for Open-Domain Question Answering
- Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
- Contributed Talk 3: LinkBERT: Pretraining Language Models with Document Links
- Invited Speaker: Chelsea Finn
- Adversarial Robustness and Cryptography
- Invited Talk 6 (Changliu Liu): Applications of Neural Verification on Robotics
- Danqi Chen
- Quoc Le
- Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis
- Invited Talk 5: Ludwig Schmidt
- DIISCO: Dynamic Intercellular Interactions in Single Cell transcriptOmics
- Invited Speaker: Andrea Bajcsy
- Invited Speaker: Jeff Schneider
- Concluding remarks
- Invited Speaker: Sergey Levine
- Community presentation 1: Robust Vision Challenge
- Community presentation 2: Challenge on Out-of-Distribution Generalization in Computer Vision
- Community presentation 3: Shifts Challenge 2.0
- Closing remarks
- Opening Remarks
- The Need for Intentions Behind Disinformation
- Invited Talk 1 (Sarthak Arora and Satyam Yadav): South Asian Feminism/s in the 21st Century: Notes on Paradoxes and Possibilities
- Networked Restless Bandits with Positive Externalities
- Invited Talk 2 (Jay Cunningham): Potentials of Community Participation in Machine Learning Research
- TBD
- Disrupting Disinformation
- Defense against Disinformation on Social Media and Its Challenges
- Invited Talk 3 (Kyra Yee): A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Modeling on Twitter
- TBD
- Multilingual Disinformation Detection for Digital Advertising
- Learning News Outlet Veracity Using Relationship Graphs
- Early Detection of Fake News on Social Media Through Propagation Path Classification
- Privacy, Security, and Obfuscation in Reporting Technologies
- Paper 3: KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients
- Paper 2: SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments
- Paper 13: From Pedestrian Detection to Crosswalk Estimation: An EM Algorithm, Analysis, and Evaluations on Diverse Datasets
- Paper 19 : Few-Shot Style Transfer for Deep Motion Forecasting
- Paper 1: MPC-based Imitation Learning for Safe and Human-like Autonomous Driving
- Paper 22: Multimodal Unsupervised Car Segmentation via Adaptive Aerial Image-to-Image Translation
- Dr. Nitesh Chawla's Talk
- Paper 17: Vision in Adverse Weather: Augmentation Using CycleGANs with Various Object Detectors for Robust Perception in Autonomous Racing
- Paper 18: Towards Long Tailed 3D Detection
- Carla P. Gomes
- Paper 21: Self-Paced Policy Optimization with Safety Constraints
- Paper 9: BiPOCO: Bi-directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection
- Paper 10: CausalAF: Causal Autoregressive Flow for Safety-Critical Scenes Generation
- Paper 6: Improving Autonomous Driving Policy Generalization via Neural Network Over-Parameterization
- Paper 5: Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging
- Paper 4: A Reinforcement Learning Attention Agent for Lidar-based 3D Object Detector
Talks & Panel Discussions
Transitions to Poster Session
Tutorials
- Quantitative Reasoning About Data Privacy in Machine Learning
- Causality and Deep Learning: Synergies, Challenges and the Future
- Validity, Reliability, and Significance: A Tutorial on Statistical Methods for Reproducible Machine Learning
- Bridging Learning and Decision Making
- Learning for Interactive Agents
- Climate Change and Machine Learning: Opportunities, Challenges, and Considerations
- Bridging Learning and Decision Making: Part I
- Bridging Learning and Decision Making: Part II
- Sampling as First-Order Optimization over a space of probability measures
- Welcome to the "Big Model" Era: Techniques and Systems to Train and Serve Bigger Models
- Causal Fairness Analysis
Virtual Keynotes
Virtual Presentation (Sponsor)s
Virtual invited talks
Welcome note by workshop organizers
Workshops
- The 1st Workshop on Healthcare AI and COVID-19
- ICML 2022 Workshop on Computational Biology
- Adaptive Experimental Design and Active Learning in the Real World
- Beyond Bayes: Paths Towards Universal Reasoning Systems
- DataPerf: Benchmarking Data for Data-Centric AI
- Knowledge Retrieval and Language Models
- Workshop on Formal Verification of Machine Learning
- Topology, Algebra, and Geometry in Machine Learning (TAG-ML)
- ICML workshop on Machine Learning for Cybersecurity (ICML-ML4Cyber)
- Machine Learning for Astrophysics
- Spurious correlations, Invariance, and Stability (SCIS)
- 1st ICML 2022 Workshop on Safe Learning for Autonomous Driving (SL4AD)
- New Frontiers in Adversarial Machine Learning
- Machine Learning for Audio Synthesis
- Dynamic Neural Networks
- Shift happens: Crowdsourcing metrics and test datasets beyond ImageNet
- Decision Awareness in Reinforcement Learning
- Workshop on Machine Learning in Computational Design
- Theory and Practice of Differential Privacy
- AI for Agent-Based Modelling (AI4ABM)
- Complex feedback in online learning
- Hardware-aware efficient training (HAET)
- The First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward
- Updatable Machine Learning
- Workshop on Human-Machine Collaboration and Teaming
- Responsible Decision Making in Dynamic Environments
- Principles of Distribution Shift (PODS)
- The ICML Expressive Vocalizations (ExVo) Workshop and Competition 2022
- Disinformation Countermeasures and Machine Learning (DisCoML)
- AI for Science
- Continuous Time Perspectives in Machine Learning
- 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH)
- Workshop on Distribution-Free Uncertainty Quantification
Report issues here.
Successful Page Load