Skip to yearly menu bar Skip to main content


Show Detail
Schedule Mon Tue Wed Thu Fri Sat
Timezone:
America/Los_Angeles
 
Filter Rooms:  

 

SUN 12 JUL
12:15 a.m.
:
Structure-to-Modular NAS
:
Machine Learning for Drug Discovery in the era of SARS-CoV-2. A panel discussion
1:30 a.m.
:
NAS Technology at Huawei
:
Google Dataset Search: Building an open ecosystem for dataset discovery
2:45 a.m.
:
End-to-end Bayesian inference workflows in TensorFlow Probability
4 a.m.
:
PaddlePaddle – An industry-grade end-to-end deep learning platform
:
On-Device Machine Learning with Apple
5:15 a.m.
:
Data-Driven based Keyword Matching Paradigm in Baidu's Sponsored Search
:
Introducing the AI Model Efficiency Toolkit (AIMET)
6:30 a.m.
:
Federated Reinforcement Learning for Financial Portfolio Optimization Using the IBM Federated Learning (IFL) Platform
:
Baidu AutoDL: Automated and Interpretable Deep Learning
7:45 a.m.
:
Structure-to-Modular NAS
:
How We Leverage Machine Learning and AI to Develop Life-Changing Medicines - A Case Study with COVID-19.
:
AutoAI at IBM Research
9 a.m.
:
NAS Technology at Huawei
:
Machine Learning in Health: What’s next?
:
RXNMapper – AI Explainability 360 - Command Line AI – COVID-19 Molecule Explorer
10:15 a.m.
:
Baidu AutoDL: Automated and Interpretable Deep Learning
:
Machine Learning for Drug Discovery in the era of SARS-CoV-2. A panel discussion
11:30 a.m.
:
PaddlePaddle – An industry-grade end-to-end deep learning platform
:
On-Device Machine Learning with Apple
12:45 p.m.
:
Data-Driven based Keyword Matching Paradigm in Baidu's Sponsored Search
:
Introducing the AI Model Efficiency Toolkit (AIMET)
2 p.m.
:
Federated Reinforcement Learning for Financial Portfolio Optimization Using the IBM Federated Learning (IFL) Platform
:
Google Dataset Search: Building an open ecosystem for dataset discovery
3:15 p.m.
:
AutoAI at IBM Research
:
End-to-end Bayesian inference workflows in TensorFlow Probability
4:30 p.m.
:
RXNMapper – AI Explainability 360 - Command Line AI – COVID-19 Molecule Explorer
11 p.m.
Affinity Workshop:
Women in Machine Learning Un-Workshop
(ends 3:00 PM)
MON 13 JUL
1 a.m.
Tutorials 1 [1:00-3:30]
Machine Learning for Healthcare: Challenges, Methods, Frontiers
Machine Learning with Signal Processing
Representation Learning Without Labels
(duration 2.5 hr)
3 a.m.
Tutorials 2 [3:00-5:30]
(duration 2.5 hr)
4 a.m.
Affinity Workshop:
New In ML
(ends 9:00 AM)
Test Of Time:
Test of Time: Gaussian Process Optimization in the Bandit Settings: No Regret and Experimental Design
(duration 1.0 hr)
5 a.m.
Affinity Workshop:
LatinX in AI Workshop
(ends 5:15 PM)
8 a.m.
Tutorials 3 [8:00-10:30]
Bayesian Deep Learning and a Probabilistic Perspective of Model Construction
Submodular Optimization: From Discrete to Continuous and Back
Model-Based Methods in Reinforcement Learning
(duration 2.5 hr)
11 a.m.
Tutorials 1 [1:00-3:30]
Machine Learning for Healthcare: Challenges, Methods, Frontiers
Machine Learning with Signal Processing
Representation Learning Without Labels
(duration 2.5 hr)
1 p.m.
Tutorials 2 [3:00-5:30]
(duration 2.5 hr)
2 p.m.
Test Of Time:
Test of Time: Gaussian Process Optimization in the Bandit Settings: No Regret and Experimental Design
(duration 1.0 hr)
Award:
Welcome and Paper Awards
(ends 3:00 PM)
Affinity Workshop:
Queer in AI
(ends 2:00 AM)
Affinity Workshop:
Joint Affinity Groups' Poster Session with Latinx in AI and Queer in AI
(ends 4:00 PM)
6 p.m.
Tutorials 3 [8:00-10:30]
Bayesian Deep Learning and a Probabilistic Perspective of Model Construction
Submodular Optimization: From Discrete to Continuous and Back
Model-Based Methods in Reinforcement Learning
(duration 2.5 hr)
TUE 14 JUL
5 a.m.
Invited Talk:
Doing Some Good with Machine Learning
Lester Mackey
(duration 2.0 hr)
7 a.m.
Poster Session 1 [7:00-7:45]
From Importance Sampling to Doubly Robust Policy Gradient
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
ControlVAE: Controllable Variational Autoencoder
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
A Simple Framework for Contrastive Learning of Visual Representations
Fast and Private Submodular and $k$-Submodular Functions Maximization with Matroid Constraints
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
Laplacian Regularized Few-Shot Learning
Self-Concordant Analysis of Frank-Wolfe Algorithms
Learning with Multiple Complementary Labels
Mutual Transfer Learning for Massive Data
Improving Generative Imagination in Object-Centric World Models
Evaluating the Performance of Reinforcement Learning Algorithms
Individual Fairness for k-Clustering
Familywise Error Rate Control by Interactive Unmasking
Data Amplification: Instance-Optimal Property Estimation
Private Reinforcement Learning with PAC and Regret Guarantees
Distance Metric Learning with Joint Representation Diversification
LEEP: A New Measure to Evaluate Transferability of Learned Representations
Reverse-engineering deep ReLU networks
Learning from Irregularly-Sampled Time Series: A Missing Data Perspective
Streaming k-Submodular Maximization under Noise subject to Size Constraint
Nested Subspace Arrangement for Representation of Relational Data
On Implicit Regularization in $\beta$-VAEs
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
Fair Learning with Private Demographic Data
Combinatorial Pure Exploration for Dueling Bandit
What Can Learned Intrinsic Rewards Capture?
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
Interpolation between Residual and Non-Residual Networks
Loss Function Search for Face Recognition
The Effect of Natural Distribution Shift on Question Answering Models
Full Law Identification in Graphical Models of Missing Data: Completeness Results
A Free-Energy Principle for Representation Learning
Generating Programmatic Referring Expressions via Program Synthesis
MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time
Stochastic Regret Minimization in Extensive-Form Games
On Second-Order Group Influence Functions for Black-Box Predictions
Scalable Nearest Neighbor Search for Optimal Transport
Recurrent Hierarchical Topic-Guided RNN for Language Generation
Problems with Shapley-value-based explanations as feature importance measures
Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
Efficient nonparametric statistical inference on population feature importance using Shapley values
PENNI: Pruned Kernel Sharing for Efficient CNN Inference
Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
On the Generalization Effects of Linear Transformations in Data Augmentation
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
Towards Understanding the Dynamics of the First-Order Adversaries
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis
Collaborative Machine Learning with Incentive-Aware Model Rewards
Randomized Smoothing of All Shapes and Sizes
Improving the Gating Mechanism of Recurrent Neural Networks
Maximum-and-Concatenation Networks
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Stochastic Optimization for Non-convex Inf-Projection Problems
Generative Flows with Matrix Exponential
Searching to Exploit Memorization Effect in Learning with Noisy Labels
Optimizing for the Future in Non-Stationary MDPs
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits
Multigrid Neural Memory
FedBoost: A Communication-Efficient Algorithm for Federated Learning
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
Tensor denoising and completion based on ordinal observations
Approximation Guarantees of Local Search Algorithms via Localizability of Set Functions
Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension
Taylor Expansion Policy Optimization
Layered Sampling for Robust Optimization Problems
Causal Strategic Linear Regression
Simple and Deep Graph Convolutional Networks
Two Routes to Scalable Credit Assignment without Weight Symmetry
Bayesian Optimisation over Multiple Continuous and Categorical Inputs
Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Deep Divergence Learning
Manifold Identification for Ultimately Communication-Efficient Distributed Optimization
DeltaGrad: Rapid retraining of machine learning models
The Buckley-Osthus model and the block preferential attachment model: statistical analysis and application
On the Noisy Gradient Descent that Generalizes as SGD
Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study
Faster Graph Embeddings via Coarsening
Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
FetchSGD: Communication-Efficient Federated Learning with Sketching
Fair Generative Modeling via Weak Supervision
Online Learning for Active Cache Synchronization
Explaining Groups of Points in Low-Dimensional Representations
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
Q-value Path Decomposition for Deep Multiagent Reinforcement Learning
Semismooth Newton Algorithm for Efficient Projections onto $\ell_{1, \infty}$-norm Ball
Confidence-Aware Learning for Deep Neural Networks
Provably Efficient Exploration in Policy Optimization
LTF: A Label Transformation Framework for Correcting Label Shift
Minimax Rate for Learning From Pairwise Comparisons in the BTL Model
Contrastive Multi-View Representation Learning on Graphs
Differentiating through the Fréchet Mean
Asynchronous Coagent Networks
Accelerated Stochastic Gradient-free and Projection-free Methods
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm
Customizing ML Predictions for Online Algorithms
Variational Bayesian Quantization
Evaluating Lossy Compression Rates of Deep Generative Models
Zeno++: Robust Fully Asynchronous SGD
On the Global Optimality of Model-Agnostic Meta-Learning
Training Binary Neural Networks through Learning with Noisy Supervision
Expert Learning through Generalized Inverse Multiobjective Optimization: Models, Insights, and Algorithms
On Variational Learning of Controllable Representations for Text without Supervision
Streaming Submodular Maximization under a k-Set System Constraint
(ends 7:45 AM)
8 a.m.
Poster Session 2 [8:00-8:45]
Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards
Estimating the Number and Effect Sizes of Non-null Hypotheses
Adversarial Neural Pruning with Latent Vulnerability Suppression
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
Angular Visual Hardness
Stronger and Faster Wasserstein Adversarial Attacks
Oracle Efficient Private Non-Convex Optimization
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
Closing the convergence gap of SGD without replacement
An end-to-end approach for the verification problem: learning the right distance
Discount Factor as a Regularizer in Reinforcement Learning
Detecting Out-of-Distribution Examples with Gram Matrices
DROCC: Deep Robust One-Class Classification
Boosting for Control of Dynamical Systems
Parameterized Rate-Distortion Stochastic Encoder
Parametric Gaussian Process Regressors
Feature Noise Induces Loss Discrepancy Across Groups
Batch Reinforcement Learning with Hyperparameter Gradients
Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
Strategyproof Mean Estimation from Multiple-Choice Questions
Nonparametric Score Estimators
Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate
Is Local SGD Better than Minibatch SGD?
Near-optimal sample complexity bounds for learning Latent $k-$polytopes and applications to Ad-Mixtures
Working Memory Graphs
Finite-Time Convergence in Continuous-Time Optimization
An EM Approach to Non-autoregressive Conditional Sequence Generation
The Tree Ensemble Layer: Differentiability meets Conditional Computation
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
Representations for Stable Off-Policy Reinforcement Learning
Online Pricing with Offline Data: Phase Transition and Inverse Square Law
Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
Differentially Private Set Union
Neural Clustering Processes
Meta-learning for Mixed Linear Regression
Invariant Risk Minimization Games
Efficient Identification in Linear Structural Causal Models with Auxiliary Cutsets
On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
Distributed Online Optimization over a Heterogeneous Network
NADS: Neural Architecture Distribution Search for Uncertainty Awareness
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
Overfitting in adversarially robust deep learning
Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
(ends 8:45 AM)
9 a.m.
Poster Session 3 [9:00-9:45]
Neural Contextual Bandits with UCB-based Exploration
Streaming Coresets for Symmetric Tensor Factorization
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Fast OSCAR and OWL Regression via Safe Screening Rules
Tightening Exploration in Upper Confidence Reinforcement Learning
BoXHED: Boosted eXact Hazard Estimator with Dynamic covariates
Low-loss connection of weight vectors: distribution-based approaches
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
Structured Policy Iteration for Linear Quadratic Regulator
Recovery of Sparse Signals from a Mixture of Linear Samples
Task-Oriented Active Perception and Planning in Environments with Partially Known Semantics
Scalable Deep Generative Modeling for Sparse Graphs
Learning Algebraic Multigrid Using Graph Neural Networks
A Markov Decision Process Model for Socio-Economic Systems Impacted by Climate Change
Disentangling Trainability and Generalization in Deep Neural Networks
Enhanced POET: Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
Being Bayesian about Categorical Probability
The Many Shapley Values for Model Explanation
Variable Skipping for Autoregressive Range Density Estimation
Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning
On Semi-parametric Inference for BART
Two Simple Ways to Learn Individual Fairness Metrics from Data
Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
Source Separation with Deep Generative Priors
Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach
How Good is the Bayes Posterior in Deep Neural Networks Really?
Context Aware Local Differential Privacy
Stabilizing Differentiable Architecture Search via Perturbation-based Regularization
An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Description Based Text Classification with Reinforcement Learning
Robustness to Spurious Correlations via Human Annotations
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
Nearly Linear Row Sampling Algorithm for Quantile Regression
Provable guarantees for decision tree induction: the agnostic setting
Lookahead-Bounded Q-learning
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
Variance Reduction in Stochastic Particle-Optimization Sampling
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Deep k-NN for Noisy Labels
Retrieval Augmented Language Model Pre-Training
Bayesian Graph Neural Networks with Adaptive Connection Sampling
Non-Autoregressive Neural Text-to-Speech
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination
A Chance-Constrained Generative Framework for Sequence Optimization
LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
Feature Quantization Improves GAN Training
Learning and Sampling of Atomic Interventions from Observations
Fiduciary Bandits
Hierarchically Decoupled Imitation For Morphological Transfer
Obtaining Adjustable Regularization for Free via Iterate Averaging
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
Variational Imitation Learning with Diverse-quality Demonstrations
Inverse Active Sensing: Modeling and Understanding Timely Decision-Making
(ends 9:45 AM)
10 a.m.
Poster Session 4 [10:00-10:45]
Revisiting Spatial Invariance with Low-Rank Local Connectivity
How recurrent networks implement contextual processing in sentiment analysis
On Learning Sets of Symmetric Elements
Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learning
Incremental Sampling Without Replacement for Sequence Models
Learning To Stop While Learning To Predict
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Automatic Shortcut Removal for Self-Supervised Representation Learning
Structured Prediction with Partial Labelling through the Infimum Loss
Online Control of the False Coverage Rate and False Sign Rate
Federated Learning with Only Positive Labels
Optimal Robust Learning of Discrete Distributions from Batches
Harmonic Decompositions of Convolutional Networks
SoftSort: A Continuous Relaxation for the argsort Operator
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Selective Dyna-style Planning Under Limited Model Capacity
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
Fully Parallel Hyperparameter Search: Reshaped Space-Filling
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
Explainable k-Means and k-Medians Clustering
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis
Training Deep Energy-Based Models with f-Divergence Minimization
Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing
Error Estimation for Sketched SVD via the Bootstrap
A simpler approach to accelerated optimization: iterative averaging meets optimism
Global Concavity and Optimization in a Class of Dynamic Discrete Choice Models
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
On the Theoretical Properties of the Network Jackknife
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Deep Isometric Learning for Visual Recognition
Logarithmic Regret for Adversarial Online Control
Generative Pretraining From Pixels
Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Topological Autoencoders
When are Non-Parametric Methods Robust?
(ends 10:45 AM)
11 a.m.
Poster Session 5 [11:00-11:45]
Understanding and Mitigating the Tradeoff between Robustness and Accuracy
Adversarial Robustness for Code
Smaller, more accurate regression forests using tree alternating optimization
Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation
LowFER: Low-rank Bilinear Pooling for Link Prediction
When Explanations Lie: Why Many Modified BP Attributions Fail
Optimal Non-parametric Learning in Repeated Contextual Auctions with Strategic Buyer
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
Optimization and Analysis of the pAp@k Metric for Recommender Systems
Near-linear time Gaussian process optimization with adaptive batching and resparsification
Learning Deep Kernels for Non-Parametric Two-Sample Tests
A Swiss Army Knife for Minimax Optimal Transport
Bandits with Adversarial Scaling
Consistent Structured Prediction with Max-Min Margin Markov Networks
Domain Adaptive Imitation Learning
Online metric algorithms with untrusted predictions
Quantum Expectation-Maximization for Gaussian mixture models
Causal Structure Discovery from Distributions Arising from Mixtures of DAGs
Stochastically Dominant Distributional Reinforcement Learning
Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimation
Information-Theoretic Local Minima Characterization and Regularization
Which Tasks Should Be Learned Together in Multi-task Learning?
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
Kernel Methods for Cooperative Multi-Agent Contextual Bandits
Explainable and Discourse Topic-aware Neural Language Understanding
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
(ends 11:45 AM)
noon
Poster Session 6 [12:00-12:45]
(ends 12:45 PM)
1 p.m.
Poster Session 7 [1:00-1:45]
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
Generalization to New Actions in Reinforcement Learning
Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise
Inertial Block Proximal Methods for Non-Convex Non-Smooth Optimization
Constant Curvature Graph Convolutional Networks
Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses
Online Convex Optimization in the Random Order Model
Bayesian Differential Privacy for Machine Learning
Temporal Logic Point Processes
StochasticRank: Global Optimization of Scale-Free Discrete Functions
The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture
Near-Tight Margin-Based Generalization Bounds for Support Vector Machines
Optimal Randomized First-Order Methods for Least-Squares Problems
Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions
Growing Action Spaces
Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
Sequential Transfer in Reinforcement Learning with a Generative Model
An Explicitly Relational Neural Network Architecture
Adaptive Sampling for Estimating Probability Distributions
Graph Random Neural Features for Distance-Preserving Graph Representations
Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery
Linear Mode Connectivity and the Lottery Ticket Hypothesis
Inexact Tensor Methods with Dynamic Accuracies
Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning
Predictive Sampling with Forecasting Autoregressive Models
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?
Implicit differentiation of Lasso-type models for hyperparameter optimization
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
Likelihood-free MCMC with Amortized Approximate Ratio Estimators
Supervised learning: no loss no cry
GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
Meta-learning with Stochastic Linear Bandits
Non-Stationary Delayed Bandits with Intermediate Observations
(ends 1:45 PM)
2 p.m.
Poster Session 8 [2:00-2:45]
Knowing The What But Not The Where in Bayesian Optimization
Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure
Debiased Sinkhorn barycenters
Learning Similarity Metrics for Numerical Simulations
Improving Molecular Design by Stochastic Iterative Target Augmentation
On the Iteration Complexity of Hypergradient Computation
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
Extreme Multi-label Classification from Aggregated Labels
Thompson Sampling via Local Uncertainty
Infinite attention: NNGP and NTK for deep attention networks
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
Why bigger is not always better: on finite and infinite neural networks
Voice Separation with an Unknown Number of Multiple Speakers
Training Neural Networks for and by Interpolation
Finding trainable sparse networks through Neural Tangent Transfer
Near Input Sparsity Time Kernel Embeddings via Adaptive Sampling
Learning Reasoning Strategies in End-to-End Differentiable Proving
Decentralised Learning with Random Features and Distributed Gradient Descent
Fast Differentiable Sorting and Ranking
Continuously Indexed Domain Adaptation
Why Are Learned Indexes So Effective?
Optimal Estimator for Unlabeled Linear Regression
Simple and sharp analysis of k-means||
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
(ends 2:45 PM)
3 p.m.
Poster Session 9 [3:00-3:45]
(ends 3:45 PM)
4 p.m.
Invited Talk:
Doing Some Good with Machine Learning
Lester Mackey
(duration 2.0 hr)
6 p.m.
Poster Session 10 [6:00-6:45]
From Importance Sampling to Doubly Robust Policy Gradient
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
ControlVAE: Controllable Variational Autoencoder
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks
A Simple Framework for Contrastive Learning of Visual Representations
Fast and Private Submodular and $k$-Submodular Functions Maximization with Matroid Constraints
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
Laplacian Regularized Few-Shot Learning
Mutual Transfer Learning for Massive Data
Improving Generative Imagination in Object-Centric World Models
Evaluating the Performance of Reinforcement Learning Algorithms
Individual Fairness for k-Clustering
Familywise Error Rate Control by Interactive Unmasking
Reverse-engineering deep ReLU networks
Learning from Irregularly-Sampled Time Series: A Missing Data Perspective
Streaming k-Submodular Maximization under Noise subject to Size Constraint
Nested Subspace Arrangement for Representation of Relational Data
On Implicit Regularization in $\beta$-VAEs
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
Fair Learning with Private Demographic Data
What Can Learned Intrinsic Rewards Capture?
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
The Effect of Natural Distribution Shift on Question Answering Models
Full Law Identification in Graphical Models of Missing Data: Completeness Results
A Free-Energy Principle for Representation Learning
Generating Programmatic Referring Expressions via Program Synthesis
Stochastic Regret Minimization in Extensive-Form Games
Scalable Nearest Neighbor Search for Optimal Transport
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
PENNI: Pruned Kernel Sharing for Efficient CNN Inference
Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
On the Generalization Effects of Linear Transformations in Data Augmentation
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
Towards Understanding the Dynamics of the First-Order Adversaries
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Stochastic Optimization for Non-convex Inf-Projection Problems
Optimizing for the Future in Non-Stationary MDPs
Multigrid Neural Memory
FedBoost: A Communication-Efficient Algorithm for Federated Learning
Tensor denoising and completion based on ordinal observations
Approximation Guarantees of Local Search Algorithms via Localizability of Set Functions
Taylor Expansion Policy Optimization
Causal Strategic Linear Regression
Bayesian Optimisation over Multiple Continuous and Categorical Inputs
Deep Divergence Learning
DeltaGrad: Rapid retraining of machine learning models
On the Noisy Gradient Descent that Generalizes as SGD
Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Faster Graph Embeddings via Coarsening
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
FetchSGD: Communication-Efficient Federated Learning with Sketching
Online Learning for Active Cache Synchronization
Explaining Groups of Points in Low-Dimensional Representations
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
Q-value Path Decomposition for Deep Multiagent Reinforcement Learning
Confidence-Aware Learning for Deep Neural Networks
Provably Efficient Exploration in Policy Optimization
Minimax Rate for Learning From Pairwise Comparisons in the BTL Model
Contrastive Multi-View Representation Learning on Graphs
Differentiating through the Fréchet Mean
Asynchronous Coagent Networks
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
Variational Bayesian Quantization
Evaluating Lossy Compression Rates of Deep Generative Models
On the Global Optimality of Model-Agnostic Meta-Learning
Streaming Submodular Maximization under a k-Set System Constraint
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Learning to Learn Kernels with Variational Random Features
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
Learning De-biased Representations with Biased Representations
Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent space
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation
Logistic Regression for Massive Data with Rare Events
Efficiently Learning Adversarially Robust Halfspaces with Noise
Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
Learning with Feature and Distribution Evolvable Streams
Intrinsic Reward Driven Imitation Learning via Generative Model
Accelerating the diffusion-based ensemble sampling by non-reversible dynamics
Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models
Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its Parallelization
(ends 6:45 PM)
7 p.m.
Poster Session 11 [7:00-7:45]
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
Learning with Multiple Complementary Labels
Distance Metric Learning with Joint Representation Diversification
LEEP: A New Measure to Evaluate Transferability of Learned Representations
Combinatorial Pure Exploration for Dueling Bandit
Interpolation between Residual and Non-Residual Networks
Loss Function Search for Face Recognition
On Second-Order Group Influence Functions for Black-Box Predictions
Problems with Shapley-value-based explanations as feature importance measures
Efficient nonparametric statistical inference on population feature importance using Shapley values
Randomized Smoothing of All Shapes and Sizes
Improving the Gating Mechanism of Recurrent Neural Networks
Maximum-and-Concatenation Networks
Searching to Exploit Memorization Effect in Learning with Noisy Labels
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
Layered Sampling for Robust Optimization Problems
Simple and Deep Graph Convolutional Networks
Manifold Identification for Ultimately Communication-Efficient Distributed Optimization
The Buckley-Osthus model and the block preferential attachment model: statistical analysis and application
Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data
LTF: A Label Transformation Framework for Correcting Label Shift
An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm
Customizing ML Predictions for Online Algorithms
Zeno++: Robust Fully Asynchronous SGD
Expert Learning through Generalized Inverse Multiobjective Optimization: Models, Insights, and Algorithms
On Variational Learning of Controllable Representations for Text without Supervision
Estimating the Number and Effect Sizes of Non-null Hypotheses
Angular Visual Hardness
Stronger and Faster Wasserstein Adversarial Attacks
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
An end-to-end approach for the verification problem: learning the right distance
Detecting Out-of-Distribution Examples with Gram Matrices
Boosting for Control of Dynamical Systems
Parametric Gaussian Process Regressors
Feature Noise Induces Loss Discrepancy Across Groups
Batch Reinforcement Learning with Hyperparameter Gradients
Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources
Strategyproof Mean Estimation from Multiple-Choice Questions
Is Local SGD Better than Minibatch SGD?
Finite-Time Convergence in Continuous-Time Optimization
An EM Approach to Non-autoregressive Conditional Sequence Generation
The Tree Ensemble Layer: Differentiability meets Conditional Computation
Representations for Stable Off-Policy Reinforcement Learning
Online Pricing with Offline Data: Phase Transition and Inverse Square Law
Differentially Private Set Union
Neural Clustering Processes
Invariant Risk Minimization Games
Efficient Identification in Linear Structural Causal Models with Auxiliary Cutsets
On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness
Distributed Online Optimization over a Heterogeneous Network
NADS: Neural Architecture Distribution Search for Uncertainty Awareness
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
Overfitting in adversarially robust deep learning
Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
(ends 7:45 PM)
8 p.m.
Poster Session 12 [8:00-8:45]
Self-Concordant Analysis of Frank-Wolfe Algorithms
Data Amplification: Instance-Optimal Property Estimation
Private Reinforcement Learning with PAC and Regret Guarantees
MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time
Recurrent Hierarchical Topic-Guided RNN for Language Generation
Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs
Collaborative Machine Learning with Incentive-Aware Model Rewards
Generative Flows with Matrix Exponential
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits
Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension
Two Routes to Scalable Credit Assignment without Weight Symmetry
Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study
Fair Generative Modeling via Weak Supervision
Semismooth Newton Algorithm for Efficient Projections onto $\ell_{1, \infty}$-norm Ball
Accelerated Stochastic Gradient-free and Projection-free Methods
Training Binary Neural Networks through Learning with Noisy Supervision
Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
Parameterized Rate-Distortion Stochastic Encoder
Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate
Fast OSCAR and OWL Regression via Safe Screening Rules
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
Structured Policy Iteration for Linear Quadratic Regulator
Task-Oriented Active Perception and Planning in Environments with Partially Known Semantics
Scalable Deep Generative Modeling for Sparse Graphs
Enhanced POET: Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning
Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
Source Separation with Deep Generative Priors
Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach
Stabilizing Differentiable Architecture Search via Perturbation-based Regularization
An Investigation of Why Overparameterization Exacerbates Spurious Correlations
Nearly Linear Row Sampling Algorithm for Quantile Regression
Provable guarantees for decision tree induction: the agnostic setting
Lookahead-Bounded Q-learning
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Retrieval Augmented Language Model Pre-Training
Bayesian Graph Neural Networks with Adaptive Connection Sampling
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination
A Chance-Constrained Generative Framework for Sequence Optimization
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
Feature Quantization Improves GAN Training
Learning and Sampling of Atomic Interventions from Observations
Hierarchically Decoupled Imitation For Morphological Transfer
Obtaining Adjustable Regularization for Free via Iterate Averaging
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
Variational Imitation Learning with Diverse-quality Demonstrations
(ends 8:45 PM)
9 p.m.
Poster Session 13 [9:00-9:45]
Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards
Adversarial Neural Pruning with Latent Vulnerability Suppression
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
Oracle Efficient Private Non-Convex Optimization
Closing the convergence gap of SGD without replacement
Discount Factor as a Regularizer in Reinforcement Learning
DROCC: Deep Robust One-Class Classification
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
Nonparametric Score Estimators
Near-optimal sample complexity bounds for learning Latent $k-$polytopes and applications to Ad-Mixtures
Working Memory Graphs
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
Meta-learning for Mixed Linear Regression
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
Variable Skipping for Autoregressive Range Density Estimation
Two Simple Ways to Learn Individual Fairness Metrics from Data
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models
Fiduciary Bandits
Revisiting Spatial Invariance with Low-Rank Local Connectivity
Incremental Sampling Without Replacement for Sequence Models
Learning To Stop While Learning To Predict
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Online Control of the False Coverage Rate and False Sign Rate
Optimal Robust Learning of Discrete Distributions from Batches
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis
Training Deep Energy-Based Models with f-Divergence Minimization
Global Concavity and Optimization in a Class of Dynamic Discrete Choice Models
On the Theoretical Properties of the Network Jackknife
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Logarithmic Regret for Adversarial Online Control
Generative Pretraining From Pixels
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
When are Non-Parametric Methods Robust?
(ends 9:45 PM)
10 p.m.
Poster Session 14 [10:00-10:45]
Neural Contextual Bandits with UCB-based Exploration
Streaming Coresets for Symmetric Tensor Factorization
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
Tightening Exploration in Upper Confidence Reinforcement Learning
BoXHED: Boosted eXact Hazard Estimator with Dynamic covariates
Low-loss connection of weight vectors: distribution-based approaches
Recovery of Sparse Signals from a Mixture of Linear Samples
Learning Algebraic Multigrid Using Graph Neural Networks
Disentangling Trainability and Generalization in Deep Neural Networks
Being Bayesian about Categorical Probability
The Many Shapley Values for Model Explanation
How Good is the Bayes Posterior in Deep Neural Networks Really?
Robustness to Spurious Correlations via Human Annotations
Non-Autoregressive Neural Text-to-Speech
LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments
SoftSort: A Continuous Relaxation for the argsort Operator
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Topological Autoencoders
Understanding and Mitigating the Tradeoff between Robustness and Accuracy
Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
Optimization and Analysis of the pAp@k Metric for Recommender Systems
Bandits with Adversarial Scaling
Consistent Structured Prediction with Max-Min Margin Markov Networks
Domain Adaptive Imitation Learning
Quantum Expectation-Maximization for Gaussian mixture models
Stochastically Dominant Distributional Reinforcement Learning
Which Tasks Should Be Learned Together in Multi-task Learning?
Kernel Methods for Cooperative Multi-Agent Contextual Bandits
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
(ends 10:45 PM)
11 p.m.
Poster Session 15 [11:00-11:45]
How recurrent networks implement contextual processing in sentiment analysis
On Learning Sets of Symmetric Elements
Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learning
Automatic Shortcut Removal for Self-Supervised Representation Learning
Structured Prediction with Partial Labelling through the Infimum Loss
Federated Learning with Only Positive Labels
Harmonic Decompositions of Convolutional Networks
Selective Dyna-style Planning Under Limited Model Capacity
Fully Parallel Hyperparameter Search: Reshaped Space-Filling
Explainable k-Means and k-Medians Clustering
Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing
Error Estimation for Sketched SVD via the Bootstrap
A simpler approach to accelerated optimization: iterative averaging meets optimism
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
Deep Isometric Learning for Visual Recognition
Differentiable Likelihoods for Fast Inversion of 'Likelihood-Free' Dynamical Systems
Adversarial Robustness for Code
When Explanations Lie: Why Many Modified BP Attributions Fail
Learning Deep Kernels for Non-Parametric Two-Sample Tests
Online metric algorithms with untrusted predictions
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
Bayesian Sparsification of Deep C-valued Networks
Learning disconnected manifolds: a no GAN's land
Word-Level Speech Recognition With a Letter to Word Encoder
SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Learning Portable Representations for High-Level Planning
(ends 11:45 PM)
WED 15 JUL
midnight
Poster Session 16 [12:00-12:45]
(ends 12:45 AM)
1 a.m.
Poster Session 17 [1:00-1:45]
Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics
Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization
Entropy Minimization In Emergent Languages
Normalizing Flows on Tori and Spheres
Restarted Bayesian Online Change-point Detector achieves Optimal Detection Delay
Partial Trace Regression and Low-Rank Kraus Decomposition
Meta-Learning with Shared Amortized Variational Inference
TaskNorm: Rethinking Batch Normalization for Meta-Learning
A distributional view on multi-objective policy optimization
Multi-step Greedy Reinforcement Learning Algorithms
On Contrastive Learning for Likelihood-free Inference
IPBoost – Non-Convex Boosting via Integer Programming
Weakly-Supervised Disentanglement Without Compromises
Ready Policy One: World Building Through Active Learning
Learning the piece-wise constant graph structure of a varying Ising model
Learning to Simulate Complex Physics with Graph Networks
Generalization to New Actions in Reinforcement Learning
Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses
Bayesian Differential Privacy for Machine Learning
Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions
Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
An Explicitly Relational Neural Network Architecture
Inexact Tensor Methods with Dynamic Accuracies
Predictive Sampling with Forecasting Autoregressive Models
Implicit differentiation of Lasso-type models for hyperparameter optimization
GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
Non-Stationary Delayed Bandits with Intermediate Observations
Learning Similarity Metrics for Numerical Simulations
Improving Molecular Design by Stochastic Iterative Target Augmentation
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
Infinite attention: NNGP and NTK for deep attention networks
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
Finding trainable sparse networks through Neural Tangent Transfer
Learning Reasoning Strategies in End-to-End Differentiable Proving
Why Are Learned Indexes So Effective?
Optimal Estimator for Unlabeled Linear Regression
(ends 1:45 AM)
2 a.m.
Poster Session 18 [2:00-2:45]
(ends 2:45 AM)
3 a.m.
Poster Session 19 [3:00-3:45]
(ends 3:45 AM)
4 a.m.
Poster Session 20 [4:00-4:45]
Thompson Sampling Algorithms for Mean-Variance Bandits
Invertible generative models for inverse problems: mitigating representation error and dataset bias
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation
Unsupervised Speech Decomposition via Triple Information Bottleneck
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations
When deep denoising meets iterative phase retrieval
Invariant Causal Prediction for Block MDPs
Interferometric Graph Transform: a Deep Unsupervised Graph Representation
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Learning to Learn Kernels with Variational Random Features
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
Learning De-biased Representations with Biased Representations
Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent space
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation
Logistic Regression for Massive Data with Rare Events
Efficiently Learning Adversarially Robust Halfspaces with Noise
Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
Learning with Feature and Distribution Evolvable Streams
Intrinsic Reward Driven Imitation Learning via Generative Model
Accelerating the diffusion-based ensemble sampling by non-reversible dynamics
Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its Parallelization
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
(ends 4:45 AM)
5 a.m.
Poster Session 21 [5:00-5:45]
Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
Message Passing Least Squares Framework and its Application to Rotation Synchronization
Learning Opinions in Social Networks
Median Matrix Completion: from Embarrassment to Optimality
Optimal approximation for unconstrained non-submodular minimization
Hierarchical Generation of Molecular Graphs using Structural Motifs
Second-Order Provable Defenses against Adversarial Attacks
Abstraction Mechanisms Predict Generalization in Deep Neural Networks
Robust and Stable Black Box Explanations
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Preference Modeling with Context-Dependent Salient Features
Optimal Bounds between f-Divergences and Integral Probability Metrics
Learnable Group Transform For Time-Series
Fair k-Centers via Maximum Matching
Privately Learning Markov Random Fields
Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
Consistent Estimators for Learning to Defer to an Expert
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
An Optimistic Perspective on Offline Deep Reinforcement Learning
The Differentiable Cross-Entropy Method
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics
Accelerating Large-Scale Inference with Anisotropic Vector Quantization
VFlow: More Expressive Generative Flows with Variational Data Augmentation
Adaptive Estimator Selection for Off-Policy Evaluation
On Learning Language-Invariant Representations for Universal Machine Translation
Channel Equilibrium Networks for Learning Deep Representation
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games
Efficient Non-conjugate Gaussian Process Factor Models for Spike Count Data using Polynomial Approximations
Efficient Intervention Design for Causal Discovery with Latents
InstaHide: Instance-hiding Schemes for Private Distributed Learning
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
One Size Fits All: Can We Train One Denoiser for All Noise Levels?
The Cost-free Nature of Optimally Tuning Tikhonov Regularizers and Other Ordered Smoothers
Reinforcement Learning for Integer Programming: Learning to Cut
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm
Adversarial Risk via Optimal Transport and Optimal Couplings
Progressive Graph Learning for Open-Set Domain Adaptation
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
Label-Noise Robust Domain Adaptation
Population-Based Black-Box Optimization for Biological Sequence Design
What can I do here? A Theory of Affordances in Reinforcement Learning
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
Learning What to Defer for Maximum Independent Sets
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Variational Label Enhancement
Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning
Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems?
Operation-Aware Soft Channel Pruning using Differentiable Masks
Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data
On Validation and Planning of An Optimal Decision Rule with Application in Healthcare Studies
Learning Quadratic Games on Networks
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
Implicit Generative Modeling for Efficient Exploration
An Accelerated DFO Algorithm for Finite-sum Convex Functions
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions
Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective
Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension
Stabilizing Transformers for Reinforcement Learning
Improved Communication Cost in Distributed PageRank Computation – A Theoretical Study
Online Bayesian Moment Matching based SAT Solver Heuristics
Private Query Release Assisted by Public Data
Robust Bayesian Classification Using An Optimistic Score Ratio
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
Causal Modeling for Fairness In Dynamical Systems
Identifying Statistical Bias in Dataset Replication
Moniqua: Modulo Quantized Communication in Decentralized SGD
Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
Sequential Cooperative Bayesian Inference
Neural Architecture Search in A Proxy Validation Loss Landscape
Causal Effect Identifiability under Partial-Observability
Data preprocessing to mitigate bias: A maximum entropy based approach
(ends 5:45 AM)
6 a.m.
Invited Talk:
Human and Machine Learning for Assistive Autonomy
Brenna Argall
(duration 2.0 hr)
8 a.m.
Poster Session 22 [8:00-8:45]
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent
On Coresets for Regularized Regression
The Non-IID Data Quagmire of Decentralized Machine Learning
Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent
Learning and Evaluating Contextual Embedding of Source Code
Optimizing Black-box Metrics with Adaptive Surrogates
Choice Set Optimization Under Discrete Choice Models of Group Decisions
Sample Amplification: Increasing Dataset Size even when Learning is Impossible
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
Inductive Relation Prediction by Subgraph Reasoning
Sparse Shrunk Additive Models
On conditional versus marginal bias in multi-armed bandits
Class-Weighted Classification: Trade-offs and Robust Approaches
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism
Planning to Explore via Self-Supervised World Models
Frustratingly Simple Few-Shot Object Detection
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Efficient Policy Learning from Surrogate-Loss Classification Reductions
Online mirror descent and dual averaging: keeping pace in the dynamic case
Strength from Weakness: Fast Learning Using Weak Supervision
Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks
Sets Clustering
Safe screening rules for L0-regression from Perspective Relaxations
Coresets for Clustering in Graphs of Bounded Treewidth
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
Randomly Projected Additive Gaussian Processes for Regression
Private Outsourced Bayesian Optimization
A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition
Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
Representing Unordered Data Using Complex-Weighted Multiset Automata
Budgeted Online Influence Maximization
Alleviating Privacy Attacks via Causal Learning
Self-Modulating Nonparametric Event-Tensor Factorization
A general recurrent state space framework for modeling neural dynamics during decision-making
Imputer: Sequence Modelling via Imputation and Dynamic Programming
(Locally) Differentially Private Combinatorial Semi-Bandits
Robust Outlier Arm Identification
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
Decoupled Greedy Learning of CNNs
Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory
Predicting deliberative outcomes
Communication-Efficient Distributed PCA by Riemannian Optimization
Structure Adaptive Algorithms for Stochastic Bandits
Stochastic Gradient and Langevin Processes
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis
Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network
Proper Network Interpretability Helps Adversarial Robustness in Classification
Adversarial Mutual Information for Text Generation
Identifying the Reward Function by Anchor Actions
Understanding Self-Training for Gradual Domain Adaptation
Adversarial Filters of Dataset Biases
Undirected Graphical Models as Approximate Posteriors
Optimal transport mapping via input convex neural networks
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Approximation Capabilities of Neural ODEs and Invertible Residual Networks
Boosting Deep Neural Network Efficiency with Dual-Module Inference
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Learning to Score Behaviors for Guided Policy Optimization
Individual Calibration with Randomized Forecasting
Predictive Multiplicity in Classification
Circuit-Based Intrinsic Methods to Detect Overfitting
Black-box Certification and Learning under Adversarial Perturbations
Negative Sampling in Semi-Supervised learning
(ends 8:45 AM)
9 a.m.
Poster Session 23 [9:00-9:45]
Structural Language Models of Code
Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Low-Variance and Zero-Variance Baselines for Extensive-Form Games
Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability
Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
Accountable Off-Policy Evaluation With Kernel Bellman Statistics
Margin-aware Adversarial Domain Adaptation with Optimal Transport
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth
Set Functions for Time Series
Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations
Hallucinative Topological Memory for Zero-Shot Visual Planning
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
Cooperative Multi-Agent Bandits with Heavy Tails
Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints
Dual Mirror Descent for Online Allocation Problems
On the consistency of top-k surrogate losses
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Leveraging Procedural Generation to Benchmark Reinforcement Learning
Flexible and Efficient Long-Range Planning Through Curious Exploration
Adversarial Robustness Against the Union of Multiple Perturbation Models
Optimal Sequential Maximization: One Interview is Enough!
Ordinal Non-negative Matrix Factorization for Recommendation
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
(ends 9:45 AM)
10 a.m.
Poster Session 24 [10:00-10:45]
Self-supervised Label Augmentation via Input Transformations
NetGAN without GAN: From Random Walks to Low-Rank Approximations
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Quantized Decentralized Stochastic Learning over Directed Graphs
Hypernetwork approach to generating point clouds
Learning to Simulate and Design for Structural Engineering
Data Valuation using Reinforcement Learning
Time-Consistent Self-Supervision for Semi-Supervised Learning
Provable Representation Learning for Imitation Learning via Bi-level Optimization
Learning Representations that Support Extrapolation
Efficiently Solving MDPs with Stochastic Mirror Descent
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks
Causal Effect Estimation and Optimal Dose Suggestions in Mobile Health
Hierarchical Verification for Adversarial Robustness
Handling the Positive-Definite Constraint in the Bayesian Learning Rule
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Learning Calibratable Policies using Programmatic Style-Consistency
Temporal Phenotyping using Deep Predictive Clustering of Disease Progression
AdaScale SGD: A User-Friendly Algorithm for Distributed Training
Stochastic bandits with arm-dependent delays
The Sample Complexity of Best-$k$ Items Selection from Pairwise Comparisons
A Game Theoretic Framework for Model Based Reinforcement Learning
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
Evolutionary Topology Search for Tensor Network Decomposition
How to Solve Fair k-Center in Massive Data Models
Fast computation of Nash Equilibria in Imperfect Information Games
Continuous-time Lower Bounds for Gradient-based Algorithms
Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
Small-GAN: Speeding up GAN Training using Core-Sets
Single Point Transductive Prediction
Correlation Clustering with Asymmetric Classification Errors
Batch Stationary Distribution Estimation
(ends 10:45 AM)
11 a.m.
Poster Session 25 [11:00-11:45]
(ends 11:45 AM)
noon
Poster Session 26 [12:00-12:45]
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
Scalable Differential Privacy with Certified Robustness in Adversarial Learning
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
Adaptive Sketching for Fast and Convergent Canonical Polyadic Decomposition
Too Relaxed to Be Fair
Reserve Pricing in Repeated Second-Price Auctions with Strategic Bidders
Scalable Exact Inference in Multi-Output Gaussian Processes
Adversarial Nonnegative Matrix Factorization
k-means++: few more steps yield constant approximation
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
Towards a General Theory of Infinite-Width Limits of Neural Classifiers
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Equivariant Neural Rendering
Optimal Continual Learning has Perfect Memory and is NP-hard
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent
Deep Coordination Graphs
Curvature-corrected learning dynamics in deep neural networks
My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
Training Linear Neural Networks: Non-Local Convergence and Complexity Results
DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training
A new regret analysis for Adam-type algorithms
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
Automatic Reparameterisation of Probabilistic Programs
Estimating Model Uncertainty of Neural Networks in Sparse Information Form
T-Basis: a Compact Representation for Neural Networks
Radioactive data: tracing through training
Inductive-bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters
Convergence Rates of Variational Inference in Sparse Deep Learning
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
Implicit Regularization of Random Feature Models
No-Regret Exploration in Goal-Oriented Reinforcement Learning
CoMic: Complementary Task Learning & Mimicry for Reusable Skills
Unique Properties of Flat Minima in Deep Networks
Learning to Encode Position for Transformer with Continuous Dynamical Model
(ends 12:45 PM)
1 p.m.
Poster Session 27 [1:00-1:45]
Leveraging Frequency Analysis for Deep Fake Image Recognition
Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization
State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian Processes
Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances
Boosting Frank-Wolfe by Chasing Gradients
On the Sample Complexity of Adversarial Multi-Source PAC Learning
On the Generalization Benefit of Noise in Stochastic Gradient Descent
Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge
Generalisation error in learning with random features and the hidden manifold model
Fast Adaptation to New Environments via Policy-Dynamics Value Functions
Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location
Interference and Generalization in Temporal Difference Learning
Estimating the Error of Randomized Newton Methods: A Bootstrap Approach
Scalable and Efficient Comparison-based Search without Features
Discriminative Adversarial Search for Abstractive Summarization
A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
Growing Adaptive Multi-hyperplane Machines
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
Continuous Time Bayesian Networks with Clocks
Adding seemingly uninformative labels helps in low data regimes
Self-Attentive Hawkes Process
Quantum Boosting
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Up or Down? Adaptive Rounding for Post-Training Quantization
Attentive Group Equivariant Convolutional Networks
Super-efficiency of automatic differentiation for functions defined as a minimum
Implicit Geometric Regularization for Learning Shapes
Involutive MCMC: a Unifying Framework
(ends 1:45 PM)
2 p.m.
Poster Session 28 [2:00-2:45]
(ends 2:45 PM)
3 p.m.
Poster Session 29 [3:00-3:45]
(ends 3:45 PM)
4 p.m.
Poster Session 30 [4:00-4:45]
Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
Message Passing Least Squares Framework and its Application to Rotation Synchronization
Learning Opinions in Social Networks
Hierarchical Generation of Molecular Graphs using Structural Motifs
Second-Order Provable Defenses against Adversarial Attacks
Abstraction Mechanisms Predict Generalization in Deep Neural Networks
Robust and Stable Black Box Explanations
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Preference Modeling with Context-Dependent Salient Features
Optimal Bounds between f-Divergences and Integral Probability Metrics
Learnable Group Transform For Time-Series
Fair k-Centers via Maximum Matching
Privately Learning Markov Random Fields
Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
Consistent Estimators for Learning to Defer to an Expert
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
An Optimistic Perspective on Offline Deep Reinforcement Learning
The Differentiable Cross-Entropy Method
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics
Accelerating Large-Scale Inference with Anisotropic Vector Quantization
Adaptive Estimator Selection for Off-Policy Evaluation
On Learning Language-Invariant Representations for Universal Machine Translation
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games
Efficient Non-conjugate Gaussian Process Factor Models for Spike Count Data using Polynomial Approximations
Efficient Intervention Design for Causal Discovery with Latents
InstaHide: Instance-hiding Schemes for Private Distributed Learning
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
One Size Fits All: Can We Train One Denoiser for All Noise Levels?
The Cost-free Nature of Optimally Tuning Tikhonov Regularizers and Other Ordered Smoothers
Reinforcement Learning for Integer Programming: Learning to Cut
Adversarial Risk via Optimal Transport and Optimal Couplings
Population-Based Black-Box Optimization for Biological Sequence Design
What can I do here? A Theory of Affordances in Reinforcement Learning
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning
Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data
On Validation and Planning of An Optimal Decision Rule with Application in Healthcare Studies
Learning Quadratic Games on Networks
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
Implicit Generative Modeling for Efficient Exploration
Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective
Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension
Stabilizing Transformers for Reinforcement Learning
Improved Communication Cost in Distributed PageRank Computation – A Theoretical Study
Online Bayesian Moment Matching based SAT Solver Heuristics
Private Query Release Assisted by Public Data
Robust Bayesian Classification Using An Optimistic Score Ratio
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
Causal Modeling for Fairness In Dynamical Systems
Identifying Statistical Bias in Dataset Replication
Moniqua: Modulo Quantized Communication in Decentralized SGD
Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
Sequential Cooperative Bayesian Inference
Causal Effect Identifiability under Partial-Observability
Data preprocessing to mitigate bias: A maximum entropy based approach
Safe Reinforcement Learning in Constrained Markov Decision Processes
Adversarial Robustness via Runtime Masking and Cleansing
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics
Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
Bidirectional Model-based Policy Optimization
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
On Relativistic f-Divergences
On Lp-norm Robustness of Ensemble Decision Stumps and Trees
Boosted Histogram Transform for Regression
Spread Divergence
Automated Synthetic-to-Real Generalization
Online Dense Subgraph Discovery via Blurred-Graph Feedback
Feature-map-level Online Adversarial Knowledge Distillation
Optimization from Structured Samples for Coverage Functions
Non-separable Non-stationary random fields
(ends 4:45 PM)
5 p.m.
Invited Talk:
Human and Machine Learning for Assistive Autonomy
Brenna Argall
(duration 2.0 hr)
7 p.m.
Poster Session 31 [7:00-7:45]
Median Matrix Completion: from Embarrassment to Optimality
Optimal approximation for unconstrained non-submodular minimization
VFlow: More Expressive Generative Flows with Variational Data Augmentation
Channel Equilibrium Networks for Learning Deep Representation
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
Label-Noise Robust Domain Adaptation
Learning What to Defer for Maximum Independent Sets
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems?
Operation-Aware Soft Channel Pruning using Differentiable Masks
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions
Neural Architecture Search in A Proxy Validation Loss Landscape
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent
Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent
Learning and Evaluating Contextual Embedding of Source Code
Sample Amplification: Increasing Dataset Size even when Learning is Impossible
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
Inductive Relation Prediction by Subgraph Reasoning
Sparse Shrunk Additive Models
On conditional versus marginal bias in multi-armed bandits
Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism
Planning to Explore via Self-Supervised World Models
Frustratingly Simple Few-Shot Object Detection
Efficient Policy Learning from Surrogate-Loss Classification Reductions
Online mirror descent and dual averaging: keeping pace in the dynamic case
Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks
Safe screening rules for L0-regression from Perspective Relaxations
Private Outsourced Bayesian Optimization
A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition
Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix
Representing Unordered Data Using Complex-Weighted Multiset Automata
Budgeted Online Influence Maximization
A general recurrent state space framework for modeling neural dynamics during decision-making
Imputer: Sequence Modelling via Imputation and Dynamic Programming
Robust Outlier Arm Identification
Decoupled Greedy Learning of CNNs
Predicting deliberative outcomes
Adversarial Mutual Information for Text Generation
Identifying the Reward Function by Anchor Actions
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Approximation Capabilities of Neural ODEs and Invertible Residual Networks
Boosting Deep Neural Network Efficiency with Dual-Module Inference
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Learning to Score Behaviors for Guided Policy Optimization
Individual Calibration with Randomized Forecasting
Predictive Multiplicity in Classification
Black-box Certification and Learning under Adversarial Perturbations
Negative Sampling in Semi-Supervised learning
(ends 7:45 PM)
8 p.m.
Poster Session 32 [8:00-8:45]
A Markov Decision Process Model for Socio-Economic Systems Impacted by Climate Change
On Semi-parametric Inference for BART
Context Aware Local Differential Privacy
Description Based Text Classification with Reinforcement Learning
Variance Reduction in Stochastic Particle-Optimization Sampling
Deep k-NN for Noisy Labels
Inverse Active Sensing: Modeling and Understanding Timely Decision-Making
Progressive Graph Learning for Open-Set Domain Adaptation
Variational Label Enhancement
An Accelerated DFO Algorithm for Finite-sum Convex Functions
On Coresets for Regularized Regression
Choice Set Optimization Under Discrete Choice Models of Group Decisions
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Sets Clustering
Coresets for Clustering in Graphs of Bounded Treewidth
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
Self-Modulating Nonparametric Event-Tensor Factorization
Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory
Communication-Efficient Distributed PCA by Riemannian Optimization
Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network
Proper Network Interpretability Helps Adversarial Robustness in Classification
Understanding Self-Training for Gradual Domain Adaptation
Adversarial Filters of Dataset Biases
Optimal transport mapping via input convex neural networks
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse
Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability
Accountable Off-Policy Evaluation With Kernel Bellman Statistics
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
Cooperative Multi-Agent Bandits with Heavy Tails
Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints
Dual Mirror Descent for Online Allocation Problems
On the consistency of top-k surrogate losses
Leveraging Procedural Generation to Benchmark Reinforcement Learning
Optimal Sequential Maximization: One Interview is Enough!
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
(ends 8:45 PM)
9 p.m.
Poster Session 33 [9:00-9:45]
The Non-IID Data Quagmire of Decentralized Machine Learning
Optimizing Black-box Metrics with Adaptive Surrogates
Class-Weighted Classification: Trade-offs and Robust Approaches
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Strength from Weakness: Fast Learning Using Weak Supervision
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
Randomly Projected Additive Gaussian Processes for Regression
Alleviating Privacy Attacks via Causal Learning
(Locally) Differentially Private Combinatorial Semi-Bandits
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
Structure Adaptive Algorithms for Stochastic Bandits
Stochastic Gradient and Langevin Processes
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis
Undirected Graphical Models as Approximate Posteriors
Circuit-Based Intrinsic Methods to Detect Overfitting
Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Low-Variance and Zero-Variance Baselines for Extensive-Form Games
Hallucinative Topological Memory for Zero-Shot Visual Planning
Adversarial Robustness Against the Union of Multiple Perturbation Models
Quantized Decentralized Stochastic Learning over Directed Graphs
Data Valuation using Reinforcement Learning
Provable Representation Learning for Imitation Learning via Bi-level Optimization
Learning Representations that Support Extrapolation
Efficiently Solving MDPs with Stochastic Mirror Descent
Causal Effect Estimation and Optimal Dose Suggestions in Mobile Health
Hierarchical Verification for Adversarial Robustness
Handling the Positive-Definite Constraint in the Bayesian Learning Rule
Learning Calibratable Policies using Programmatic Style-Consistency
The Sample Complexity of Best-$k$ Items Selection from Pairwise Comparisons
A Game Theoretic Framework for Model Based Reinforcement Learning
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
Small-GAN: Speeding up GAN Training using Core-Sets
Single Point Transductive Prediction
Correlation Clustering with Asymmetric Classification Errors
Batch Stationary Distribution Estimation
(ends 9:45 PM)
10 p.m.
Poster Session 34 [10:00-10:45]
Structural Language Models of Code
Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
Margin-aware Adversarial Domain Adaptation with Optimal Transport
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth
Set Functions for Time Series
Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Flexible and Efficient Long-Range Planning Through Curious Exploration
Ordinal Non-negative Matrix Factorization for Recommendation
NetGAN without GAN: From Random Walks to Low-Rank Approximations
Learning to Simulate and Design for Structural Engineering
How to Solve Fair k-Center in Massive Data Models
Continuous-time Lower Bounds for Gradient-based Algorithms
Revisiting Fundamentals of Experience Replay
On the Number of Linear Regions of Convolutional Neural Networks
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
The Shapley Taylor Interaction Index
A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation
Robust Graph Representation Learning via Neural Sparsification
The Implicit and Explicit Regularization Effects of Dropout
Multidimensional Shape Constraints
Encoding Musical Style with Transformer Autoencoders
“Other-Play” for Zero-Shot Coordination
Deep Gaussian Markov Random Fields
Proving the Lottery Ticket Hypothesis: Pruning is All You Need
Learning Near Optimal Policies with Low Inherent Bellman Error
(ends 10:45 PM)
11 p.m.
Poster Session 35 [11:00-11:45]
Self-supervised Label Augmentation via Input Transformations
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Hypernetwork approach to generating point clouds
Time-Consistent Self-Supervision for Semi-Supervised Learning
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Temporal Phenotyping using Deep Predictive Clustering of Disease Progression
AdaScale SGD: A User-Friendly Algorithm for Distributed Training
Stochastic bandits with arm-dependent delays
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
Evolutionary Topology Search for Tensor Network Decomposition
Fast computation of Nash Equilibria in Imperfect Information Games
Option Discovery in the Absence of Rewards with Manifold Analysis
DeBayes: a Bayesian Method for Debiasing Network Embeddings
Feature Selection using Stochastic Gates
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization
Too Relaxed to Be Fair
Adversarial Nonnegative Matrix Factorization
Towards a General Theory of Infinite-Width Limits of Neural Classifiers
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation
Curvature-corrected learning dynamics in deep neural networks
My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
Inductive-bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead
Learning to Encode Position for Transformer with Continuous Dynamical Model
(ends 11:45 PM)
THU 16 JUL
midnight
Poster Session 36 [12:00-12:45]
(ends 12:45 AM)
1 a.m.
Poster Session 37 [1:00-1:45]
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
Scalable Differential Privacy with Certified Robustness in Adversarial Learning
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
Adaptive Sketching for Fast and Convergent Canonical Polyadic Decomposition
Reserve Pricing in Repeated Second-Price Auctions with Strategic Bidders
Scalable Exact Inference in Multi-Output Gaussian Processes
k-means++: few more steps yield constant approximation
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
Equivariant Neural Rendering
Optimal Continual Learning has Perfect Memory and is NP-hard
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent
Deep Coordination Graphs
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
Automatic Reparameterisation of Probabilistic Programs
T-Basis: a Compact Representation for Neural Networks
Radioactive data: tracing through training
Convergence Rates of Variational Inference in Sparse Deep Learning
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
Implicit Regularization of Random Feature Models
No-Regret Exploration in Goal-Oriented Reinforcement Learning
CoMic: Complementary Task Learning & Mimicry for Reusable Skills
Unique Properties of Flat Minima in Deep Networks
On the Generalization Benefit of Noise in Stochastic Gradient Descent
Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge
Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location
Discriminative Adversarial Search for Abstractive Summarization
Adding seemingly uninformative labels helps in low data regimes
Self-Attentive Hawkes Process
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Super-efficiency of automatic differentiation for functions defined as a minimum
Involutive MCMC: a Unifying Framework
Explicit Gradient Learning for Black-Box Optimization
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing
Sparse Gaussian Processes with Spherical Harmonic Features
Multi-Precision Policy Enforced Training (MuPPET) : A Precision-Switching Strategy for Quantised Fixed-Point Training of CNNs
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
DeepCoDA: personalized interpretability for compositional health data
(ends 1:45 AM)
2 a.m.
Poster Session 38 [2:00-2:45]
(ends 2:45 AM)
3 a.m.
Poster Session 39 [3:00-3:45]
(ends 3:45 AM)
4 a.m.
Poster Session 40 [4:00-4:45]
(ends 4:45 AM)
5 a.m.
Town Hall:
Town Hall Meeting
(duration 1.0 hr)
6 a.m.
Poster Session 41 [6:00-6:45]
Acceleration through spectral density estimation
Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming
Enhancing Simple Models by Exploiting What They Already Know
Reducing Sampling Error in Batch Temporal Difference Learning
Learning the Valuations of a $k$-demand Agent
Differentiable Product Quantization for End-to-End Embedding Compression
Improving Robustness of Deep-Learning-Based Image Reconstruction
New Oracle-Efficient Algorithms for Private Synthetic Data Release
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition
Born-again Tree Ensembles
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
Learning Selection Strategies in Buchberger’s Algorithm
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models
p-Norm Flow Diffusion for Local Graph Clustering
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Do GANs always have Nash equilibria?
Error-Bounded Correction of Noisy Labels
Improving Transformer Optimization Through Better Initialization
Sparsified Linear Programming for Zero-Sum Equilibrium Finding
Amortized Finite Element Analysis for Fast PDE-Constrained Optimization
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching
Task Understanding from Confusing Multi-task Data
Privately detecting changes in unknown distributions
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
On a projective ensemble approach to two sample test for equality of distributions
Adaptive Adversarial Multi-task Representation Learning
Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation
Sharp Statistical Guaratees for Adversarially Robust Gaussian Classification
FACT: A Diagnostic for Group Fairness Trade-offs
Robust Pricing in Dynamic Mechanism Design
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
Universal Asymptotic Optimality of Polyak Momentum
Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
Graph Homomorphism Convolution
Multi-Agent Routing Value Iteration Network
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
Improved Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance
Do RNN and LSTM have Long Memory?
Estimation of Bounds on Potential Outcomes For Decision Making
Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event Data
Does label smoothing mitigate label noise?
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Tails of Lipschitz Triangular Flows
Convex Calibrated Surrogates for the Multi-Label F-Measure
Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems
Deep Reinforcement Learning with Smooth Policy
On Breaking Deep Generative Model-based Defenses and Beyond
Invariant Rationalization
Provably Efficient Model-based Policy Adaptation
Countering Language Drift with Seeded Iterated Learning
Transparency Promotion with Model-Agnostic Linear Competitors
Almost Tune-Free Variance Reduction
Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks
Causal Inference using Gaussian Processes with Structured Latent Confounders
BINOCULARS for efficient, nonmyopic sequential experimental design
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
A Pairwise Fair and Community-preserving Approach to k-Center Clustering
Fiedler Regularization: Learning Neural Networks with Graph Sparsity
Linear Lower Bounds and Conditioning of Differentiable Games
Latent Variable Modelling with Hyperbolic Normalizing Flows
Universal Equivariant Multilayer Perceptrons
T-GD: Transferable GAN-generated Images Detection Framework
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
A Flexible Framework for Nonparametric Graphical Modeling that Accommodates Machine Learning
Performative Prediction
Sparse Convex Optimization via Adaptively Regularized Hard Thresholding
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
Rigging the Lottery: Making All Tickets Winners
Meta Variance Transfer: Learning to Augment from the Others
Upper bounds for Model-Free Row-Sparse Principal Component Analysis
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
Scalable Differentiable Physics for Learning and Control
Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization
Piecewise Linear Regression via a Difference of Convex Functions
On the Expressivity of Neural Networks for Deep Reinforcement Learning
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation
Bridging the Gap Between f-GANs and Wasserstein GANs
Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics
GraphOpt: Learning Optimization Models of Graph Formation
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Constrained Markov Decision Processes via Backward Value Functions
Learning Optimal Tree Models under Beam Search
Mapping natural-language problems to formal-language solutions using structured neural representations
Optimizing Dynamic Structures with Bayesian Generative Search
Robustness to Programmable String Transformations via Augmented Abstract Training
Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization
Input-Sparsity Low Rank Approximation in Schatten Norm
Improved Sleeping Bandits with Stochastic Action Sets and Adversarial Rewards
Online Learning with Dependent Stochastic Feedback Graphs
Low-Rank Bottleneck in Multi-head Attention Models
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
Strategic Classification is Causal Modeling in Disguise
Sequence Generation with Mixed Representations
Concise Explanations of Neural Networks using Adversarial Training
Calibration, Entropy Rates, and Memory in Language Models
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks
Refined bounds for algorithm configuration: The knife-edge of dual class approximability
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
Adaptive Region-Based Active Learning
Continuous Graph Neural Networks
Robustifying Sequential Neural Processes
Bandits for BMO Functions
Black-Box Methods for Restoring Monotonicity
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
Reward-Free Exploration for Reinforcement Learning
Interpreting Robust Optimization via Adversarial Influence Functions
Learning with Bounded Instance- and Label-dependent Label Noise
Learning Robot Skills with Temporal Variational Inference
Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance
(ends 6:45 AM)
7 a.m.
Poster Session 42 [7:00-7:45]
On Leveraging Pretrained GANs for Generation with Limited Data
Multi-Objective Molecule Generation using Interpretable Substructures
Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
Simultaneous Inference for Massive Data: Distributed Bootstrap
Stochastic Hamiltonian Gradient Methods for Smooth Games
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model
On Efficient Constructions of Checkpoints
Educating Text Autoencoders: Latent Representation Guidance via Denoising
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
Model-Based Reinforcement Learning with Value-Targeted Regression
Time-aware Large Kernel Convolutions
Better depth-width trade-offs for neural networks through the lens of dynamical systems
ConQUR: Mitigating Delusional Bias in Deep Q-Learning
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
Distribution Augmentation for Generative Modeling
Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model
Doubly robust off-policy evaluation with shrinkage
On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data
Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
Momentum Improves Normalized SGD
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference
DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images
Semi-Supervised Learning with Normalizing Flows
Online Learning with Imperfect Hints
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard Models
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Efficient Continuous Pareto Exploration in Multi-Task Learning
No-Regret and Incentive-Compatible Online Learning
Lorentz Group Equivariant Neural Network for Particle Physics
Generalization via Derandomization
Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
Semi-Supervised StyleGAN for Disentanglement Learning
Adversarial Attacks on Copyright Detection Systems
ACFlow: Flow Models for Arbitrary Conditional Likelihoods
Optimal Differential Privacy Composition for Exponential Mechanisms
Graph Optimal Transport for Cross-Domain Alignment
Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos
Graph Structure of Neural Networks
Normalized Loss Functions for Deep Learning with Noisy Labels
The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation
Goodness-of-Fit Tests for Inhomogeneous Random Graphs
Online Learned Continual Compression with Adaptive Quantization Modules
Perceptual Generative Autoencoders
Goal-Aware Prediction: Learning to Model What Matters
On hyperparameter tuning in general clustering problemsm
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
Variational Inference for Sequential Data with Future Likelihood Estimates
Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is False
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models
Provable Smoothness Guarantees for Black-Box Variational Inference
Uniform Convergence of Rank-weighted Learning
Improving generalization by controlling label-noise information in neural network weights
Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
(ends 7:45 AM)
8 a.m.
Poster Session 43 [8:00-8:45]
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC
Visual Grounding of Learned Physical Models
Coresets for Data-efficient Training of Machine Learning Models
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
Minimax Pareto Fairness: A Multi Objective Perspective
An Imitation Learning Approach for Cache Replacement
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
Principled learning method for Wasserstein distributionally robust optimization with local perturbations
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
Model Fusion with Kullback--Leibler Divergence
High-dimensional Robust Mean Estimation via Gradient Descent
The Performance Analysis of Generalized Margin Maximizers on Separable Data
Emergence of Separable Manifolds in Deep Language Representations
Learning Human Objectives by Evaluating Hypothetical Behavior
Cost-Effective Interactive Attention Learning with Neural Attention Processes
SGD Learns One-Layer Networks in WGANs
Defense Through Diverse Directions
Certified Data Removal from Machine Learning Models
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Momentum-Based Policy Gradient Methods
Domain Aggregation Networks for Multi-Source Domain Adaptation
Generalized and Scalable Optimal Sparse Decision Trees
Progressive Identification of True Labels for Partial-Label Learning
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
Gradient Temporal-Difference Learning with Regularized Corrections
Sparse Sinkhorn Attention
Learning Mixtures of Graphs from Epidemic Cascades
Parameter-free, Dynamic, and Strongly-Adaptive Online Learning
Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
One-shot Distributed Ridge Regression in High Dimensions
Generalization and Representational Limits of Graph Neural Networks
Optimizing Data Usage via Differentiable Rewards
(ends 8:45 AM)
9 a.m.
Poster Session 44 [9:00-9:45]
Symbolic Network: Generalized Neural Policies for Relational MDPs
On the Global Convergence Rates of Softmax Policy Gradient Methods
Bounding the fairness and accuracy of classifiers from population statistics
Energy-Based Processes for Exchangeable Data
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
The Implicit Regularization of Stochastic Gradient Flow for Least Squares
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
ECLIPSE: An Extreme-Scale Linear Program Solver for Web-Applications
Multiclass Neural Network Minimization via Tropical Newton Polytope Approximation
Accelerated Message Passing for Entropy-Regularized MAP Inference
Aligned Cross Entropy for Non-Autoregressive Machine Translation
WaveFlow: A Compact Flow-based Model for Raw Audio
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
Inferring DQN structure for high-dimensional continuous control
Evaluating Machine Accuracy on ImageNet
From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce Model
When Does Self-Supervision Help Graph Convolutional Networks?
Decision Trees for Decision-Making under the Predict-then-Optimize Framework
Generalization Error of Generalized Linear Models in High Dimensions
Bio-Inspired Hashing for Unsupervised Similarity Search
Implicit competitive regularization in GANs
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Active World Model Learning in Agent-rich Environments with Progress Curiosity
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
A Distributional Framework For Data Valuation
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Concept Bottleneck Models
Improved Optimistic Algorithms for Logistic Bandits
Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Video Prediction via Example Guidance
(ends 9:45 AM)
10 a.m.
Invited Talk:
Quantum Machine Learning : Prospects and Challenges
Iordanis Kerenidis
(duration 2.0 hr)
noon
Poster Session 45 [12:00-12:45]
Information Particle Filter Tree: An Online Algorithm for POMDPs with Belief-Based Rewards on Continuous Domains
Inter-domain Deep Gaussian Processes
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning
Graph-based Nearest Neighbor Search: From Practice to Theory
Soft Threshold Weight Reparameterization for Learnable Sparsity
Missing Data Imputation using Optimal Transport
Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks
Learning Flat Latent Manifolds with VAEs
A Flexible Latent Space Model for Multilayer Networks
The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Low Bias Low Variance Gradient Estimates for Hierarchical Boolean Stochastic Networks
Random extrapolation for primal-dual coordinate descent
Composable Sketches for Functions of Frequencies: Beyond the Worst Case
Double-Loop Unadjusted Langevin Algorithm
Bisection-Based Pricing for Repeated Contextual Auctions against Strategic Buyer
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Monte-Carlo Tree Search as Regularized Policy Optimization
Aggregation of Multiple Knockoffs
Online Multi-Kernel Learning with Graph-Structured Feedback
Data-Efficient Image Recognition with Contrastive Predictive Coding
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
Near-optimal Regret Bounds for Stochastic Shortest Path
Conditional gradient methods for stochastically constrained convex minimization
Neural Kernels Without Tangents
Supervised Quantile Normalization for Low Rank Matrix Factorization
Online Continual Learning from Imbalanced Data
Learning to Rank Learning Curves
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Extra-gradient with player sampling for faster convergence in n-player games
Real-Time Optimisation for Online Learning in Auctions
Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
On Thompson Sampling with Langevin Algorithms
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Optimistic Bounds for Multi-output Learning
Predictive Coding for Locally-Linear Control
Randomized Block-Diagonal Preconditioning for Parallel Learning
PowerNorm: Rethinking Batch Normalization in Transformers
Gradient-free Online Learning in Continuous Games with Delayed Rewards
Naive Exploration is Optimal for Online LQR
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Topologically Densified Distributions
(ends 12:45 PM)
1 p.m.
Poster Session 46 [1:00-1:45]
(ends 1:45 PM)
2 p.m.
Poster Session 47 [2:00-2:45]
(ends 2:45 PM)
3 p.m.
Poster Session 48 [3:00-3:45]
(ends 3:45 PM)
4 p.m.
Town Hall:
Town Hall Meeting
(duration 1.0 hr)
5 p.m.
Poster Session 49 [5:00-5:45]
Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming
Enhancing Simple Models by Exploiting What They Already Know
Learning the Valuations of a $k$-demand Agent
Improving Robustness of Deep-Learning-Based Image Reconstruction
New Oracle-Efficient Algorithms for Private Synthetic Data Release
Born-again Tree Ensembles
Learning Selection Strategies in Buchberger’s Algorithm
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models
p-Norm Flow Diffusion for Local Graph Clustering
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Error-Bounded Correction of Noisy Labels
Privately detecting changes in unknown distributions
Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation
FACT: A Diagnostic for Group Fairness Trade-offs
Robust Pricing in Dynamic Mechanism Design
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
Graph Homomorphism Convolution
Multi-Agent Routing Value Iteration Network
Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
Improved Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance
Estimation of Bounds on Potential Outcomes For Decision Making
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Invariant Rationalization
Transparency Promotion with Model-Agnostic Linear Competitors
Almost Tune-Free Variance Reduction
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks
BINOCULARS for efficient, nonmyopic sequential experimental design
A Pairwise Fair and Community-preserving Approach to k-Center Clustering
Fiedler Regularization: Learning Neural Networks with Graph Sparsity
Latent Variable Modelling with Hyperbolic Normalizing Flows
Universal Equivariant Multilayer Perceptrons
A Flexible Framework for Nonparametric Graphical Modeling that Accommodates Machine Learning
Sparse Convex Optimization via Adaptively Regularized Hard Thresholding
Rigging the Lottery: Making All Tickets Winners
Upper bounds for Model-Free Row-Sparse Principal Component Analysis
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization
Scalable Differentiable Physics for Learning and Control
Piecewise Linear Regression via a Difference of Convex Functions
On the Expressivity of Neural Networks for Deep Reinforcement Learning
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation
Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics
GraphOpt: Learning Optimization Models of Graph Formation
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Constrained Markov Decision Processes via Backward Value Functions
Optimizing Dynamic Structures with Bayesian Generative Search
Online Learning with Dependent Stochastic Feedback Graphs
Low-Rank Bottleneck in Multi-head Attention Models
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
Strategic Classification is Causal Modeling in Disguise
Concise Explanations of Neural Networks using Adversarial Training
Calibration, Entropy Rates, and Memory in Language Models
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
Continuous Graph Neural Networks
Reward-Free Exploration for Reinforcement Learning
Interpreting Robust Optimization via Adversarial Influence Functions
Learning with Bounded Instance- and Label-dependent Label Noise
Learning Robot Skills with Temporal Variational Inference
Projection-free Distributed Online Convex Optimization with $O(\sqrt{T})$ Communication Complexity
Representation Learning via Adversarially-Contrastive Optimal Transport
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
Self-Attentive Associative Memory
A Graph to Graphs Framework for Retrosynthesis Prediction
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making
On the (In)tractability of Computing Normalizing Constants for the Product of Determinantal Point Processes
Minimax Weight and Q-Function Learning for Off-Policy Evaluation
Do We Need Zero Training Loss After Achieving Zero Training Error?
Multinomial Logit Bandit with Low Switching Cost
Non-autoregressive Machine Translation with Disentangled Context Transformer
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
Transformer Hawkes Process
Learning Autoencoders with Relational Regularization
Cost-effectively Identifying Causal Effects When Only Response Variable is Observable
Multi-objective Bayesian Optimization using Pareto-frontier Entropy
DropNet: Reducing Neural Network Complexity via Iterative Pruning
More Information Supervised Probabilistic Deep Face Embedding Learning
A Tree-Structured Decoder for Image-to-Markup Generation
On the Power of Compressed Sensing with Generative Models
Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
Sparse Subspace Clustering with Entropy-Norm
(ends 5:45 PM)
6 p.m.
Poster Session 50 [6:00-6:45]
Acceleration through spectral density estimation
Differentiable Product Quantization for End-to-End Embedding Compression
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
Do GANs always have Nash equilibria?
Improving Transformer Optimization Through Better Initialization
Sparsified Linear Programming for Zero-Sum Equilibrium Finding
Amortized Finite Element Analysis for Fast PDE-Constrained Optimization
Task Understanding from Confusing Multi-task Data
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
On a projective ensemble approach to two sample test for equality of distributions
Adaptive Adversarial Multi-task Representation Learning
Sharp Statistical Guaratees for Adversarially Robust Gaussian Classification
Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
Does label smoothing mitigate label noise?
Convex Calibrated Surrogates for the Multi-Label F-Measure
Deep Reinforcement Learning with Smooth Policy
Countering Language Drift with Seeded Iterated Learning
Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization
Causal Inference using Gaussian Processes with Structured Latent Confounders
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
Linear Lower Bounds and Conditioning of Differentiable Games
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
Meta Variance Transfer: Learning to Augment from the Others
Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization
Bridging the Gap Between f-GANs and Wasserstein GANs
Mapping natural-language problems to formal-language solutions using structured neural representations
Robustness to Programmable String Transformations via Augmented Abstract Training
Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization
Input-Sparsity Low Rank Approximation in Schatten Norm
Sequence Generation with Mixed Representations
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space
Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters
Refined bounds for algorithm configuration: The knife-edge of dual class approximability
Adaptive Region-Based Active Learning
Robustifying Sequential Neural Processes
Bandits for BMO Functions
Black-Box Methods for Restoring Monotonicity
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance
On Leveraging Pretrained GANs for Generation with Limited Data
Multi-Objective Molecule Generation using Interpretable Substructures
Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
Simultaneous Inference for Massive Data: Distributed Bootstrap
Stochastic Hamiltonian Gradient Methods for Smooth Games
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
On Efficient Constructions of Checkpoints
Educating Text Autoencoders: Latent Representation Guidance via Denoising
Time-aware Large Kernel Convolutions
ConQUR: Mitigating Delusional Bias in Deep Q-Learning
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model
Momentum Improves Normalized SGD
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference
DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images
Online Learning with Imperfect Hints
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard Models
Efficient Continuous Pareto Exploration in Multi-Task Learning
No-Regret and Incentive-Compatible Online Learning
Generalization via Derandomization
Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
Adversarial Attacks on Copyright Detection Systems
ACFlow: Flow Models for Arbitrary Conditional Likelihoods
Graph Optimal Transport for Cross-Domain Alignment
Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos
The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation
Online Learned Continual Compression with Adaptive Quantization Modules
Goal-Aware Prediction: Learning to Model What Matters
On hyperparameter tuning in general clustering problemsm
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is False
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models
Provable Smoothness Guarantees for Black-Box Variational Inference
Uniform Convergence of Rank-weighted Learning
Improving generalization by controlling label-noise information in neural network weights
Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
Few-shot Domain Adaptation by Causal Mechanism Transfer
On Layer Normalization in the Transformer Architecture
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
(ends 6:45 PM)
7 p.m.
Poster Session 51 [7:00-7:45]
Reducing Sampling Error in Batch Temporal Difference Learning
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching
Universal Asymptotic Optimality of Polyak Momentum
Do RNN and LSTM have Long Memory?
Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event Data
Tails of Lipschitz Triangular Flows
Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems
On Breaking Deep Generative Model-based Defenses and Beyond
Provably Efficient Model-based Policy Adaptation
T-GD: Transferable GAN-generated Images Detection Framework
Performative Prediction
Learning Optimal Tree Models under Beam Search
Improved Sleeping Bandits with Stochastic Action Sets and Adversarial Rewards
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks
A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
Model-Based Reinforcement Learning with Value-Targeted Regression
Distribution Augmentation for Generative Modeling
On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC
Visual Grounding of Learned Physical Models
Coresets for Data-efficient Training of Machine Learning Models
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
Minimax Pareto Fairness: A Multi Objective Perspective
An Imitation Learning Approach for Cache Replacement
Principled learning method for Wasserstein distributionally robust optimization with local perturbations
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
High-dimensional Robust Mean Estimation via Gradient Descent
The Performance Analysis of Generalized Margin Maximizers on Separable Data
Emergence of Separable Manifolds in Deep Language Representations
Learning Human Objectives by Evaluating Hypothetical Behavior
Cost-Effective Interactive Attention Learning with Neural Attention Processes
SGD Learns One-Layer Networks in WGANs
Defense Through Diverse Directions
Certified Data Removal from Machine Learning Models
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation
Momentum-Based Policy Gradient Methods
Domain Aggregation Networks for Multi-Source Domain Adaptation
Generalized and Scalable Optimal Sparse Decision Trees
Progressive Identification of True Labels for Partial-Label Learning
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
Gradient Temporal-Difference Learning with Regularized Corrections
Sparse Sinkhorn Attention
Learning Mixtures of Graphs from Epidemic Cascades
Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
One-shot Distributed Ridge Regression in High Dimensions
Generalization and Representational Limits of Graph Neural Networks
Optimizing Data Usage via Differentiable Rewards
(ends 7:45 PM)
8 p.m.
Poster Session 52 [8:00-8:45]
Better depth-width trade-offs for neural networks through the lens of dynamical systems
Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games
Doubly robust off-policy evaluation with shrinkage
Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment
Semi-Supervised Learning with Normalizing Flows
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Lorentz Group Equivariant Neural Network for Particle Physics
Semi-Supervised StyleGAN for Disentanglement Learning
Optimal Differential Privacy Composition for Exponential Mechanisms
Graph Structure of Neural Networks
Normalized Loss Functions for Deep Learning with Noisy Labels
Goodness-of-Fit Tests for Inhomogeneous Random Graphs
Perceptual Generative Autoencoders
Variational Inference for Sequential Data with Future Likelihood Estimates
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
Model Fusion with Kullback--Leibler Divergence
Parameter-free, Dynamic, and Strongly-Adaptive Online Learning
On the Global Convergence Rates of Softmax Policy Gradient Methods
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
The Implicit Regularization of Stochastic Gradient Flow for Least Squares
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
Accelerated Message Passing for Entropy-Regularized MAP Inference
Aligned Cross Entropy for Non-Autoregressive Machine Translation
Inferring DQN structure for high-dimensional continuous control
Evaluating Machine Accuracy on ImageNet
When Does Self-Supervision Help Graph Convolutional Networks?
Decision Trees for Decision-Making under the Predict-then-Optimize Framework
Generalization Error of Generalized Linear Models in High Dimensions
Bio-Inspired Hashing for Unsupervised Similarity Search
Implicit competitive regularization in GANs
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
Concept Bottleneck Models
Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Video Prediction via Example Guidance
(ends 8:45 PM)
11 p.m.
Invited Talk:
Quantum Machine Learning : Prospects and Challenges
Iordanis Kerenidis
(duration 2.0 hr)
Poster Session 53 [11:00-11:45]
(ends 11:45 PM)
FRI 17 JUL
midnight
Poster Session 54 [12:00-12:45]
(ends 12:45 AM)
1 a.m.
Poster Session 55 [1:00-1:45]
Graph-based Nearest Neighbor Search: From Practice to Theory
The Complexity of Finding Stationary Points with Stochastic Gradient Descent
Bisection-Based Pricing for Repeated Contextual Auctions against Strategic Buyer
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Monte-Carlo Tree Search as Regularized Policy Optimization
Aggregation of Multiple Knockoffs
Data-Efficient Image Recognition with Contrastive Predictive Coding
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
Near-optimal Regret Bounds for Stochastic Shortest Path
Conditional gradient methods for stochastically constrained convex minimization
Supervised Quantile Normalization for Low Rank Matrix Factorization
Learning to Rank Learning Curves
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Extra-gradient with player sampling for faster convergence in n-player games
Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
Optimistic Bounds for Multi-output Learning
Predictive Coding for Locally-Linear Control
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Stochastic Latent Residual Video Prediction
Stochastic Differential Equations with Variational Wishart Diffusions
Predicting Choice with Set-Dependent Aggregation
A quantile-based approach for hyperparameter transfer learning
Graph Filtration Learning
Stochastic Subspace Cubic Newton Method
Neural Topic Modeling with Continual Lifelong Learning
Spectral Clustering with Graph Neural Networks for Graph Pooling
Anderson Acceleration of Proximal Gradient Methods
Scalable Gaussian Process Separation for Kernels with a Non-Stationary Phase
Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks
Extrapolation for Large-batch Training in Deep Learning
(ends 1:45 AM)
2 a.m.
Workshops Fri [2:00-8:00]
(ends 8:00 PM)
Poster Session 56 [2:00-2:45]
(ends 2:45 AM)
3 a.m.
Poster Session 57 [3:00-3:45]
(ends 3:45 AM)
4 a.m.
Poster Session 58 [4:00-4:45]
Deep Streaming Label Learning
Randomization matters How to defend against strong adversarial attacks
Neural Network Control Policy Verification With Persistent Adversarial Perturbation
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
Off-Policy Actor-Critic with Shared Experience Replay
Learning Factorized Weight Matrix for Joint Filtering
Projection-free Distributed Online Convex Optimization with $O(\sqrt{T})$ Communication Complexity
Representation Learning via Adversarially-Contrastive Optimal Transport
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
Self-Attentive Associative Memory
A Graph to Graphs Framework for Retrosynthesis Prediction
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making
On the (In)tractability of Computing Normalizing Constants for the Product of Determinantal Point Processes
Minimax Weight and Q-Function Learning for Off-Policy Evaluation
Do We Need Zero Training Loss After Achieving Zero Training Error?
Multinomial Logit Bandit with Low Switching Cost
Non-autoregressive Machine Translation with Disentangled Context Transformer
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
Transformer Hawkes Process
Learning Autoencoders with Relational Regularization
Cost-effectively Identifying Causal Effects When Only Response Variable is Observable
Multi-objective Bayesian Optimization using Pareto-frontier Entropy
DropNet: Reducing Neural Network Complexity via Iterative Pruning
More Information Supervised Probabilistic Deep Face Embedding Learning
A Tree-Structured Decoder for Image-to-Markup Generation
On the Power of Compressed Sensing with Generative Models
Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
Sparse Subspace Clustering with Entropy-Norm
Few-shot Domain Adaptation by Causal Mechanism Transfer
On Layer Normalization in the Transformer Architecture
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
(ends 4:45 AM)
SAT 18 JUL
midnight
1 a.m.
Workshops Sat [1:00-8:00]
(ends 8:00 PM)