Toggle Poster Visibility
Poster
@ Virtual
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
Expo Talk Panel
Sun Jul 18 05:00 AM -- 06:00 AM (PDT)
Machine Learning for Addressing Power Grid Congestion
Expo Workshop
Sun Jul 18 05:00 AM -- 09:30 AM (PDT)
Real World RL: Azure Personalizer & Vowpal Wabbit
Expo Workshop
Sun Jul 18 05:00 AM -- 09:00 AM (PDT)
High-Quality Data Labeling at Scale with Toloka
Expo Talk Panel
Sun Jul 18 06:00 AM -- 07:00 AM (PDT)
The latest advances and use-cases in the field of Causal AI
Expo Talk Panel
Sun Jul 18 07:00 AM -- 08:00 AM (PDT)
Unique Research Opportunities in AI Algorithms, Health, Traffic, and Weather
Expo Talk Panel
Sun Jul 18 08:00 AM -- 09:00 AM (PDT)
Cool Moves: Decoupling physical motions and self-avatar motions in Virtual Reality
Expo Demonstration
Sun Jul 18 09:00 AM -- 10:00 AM (PDT)
Neural Video Codec Demo
Expo Talk Panel
Sun Jul 18 10:00 AM -- 11:00 AM (PDT)
IBM Analog Hardware Acceleration Kit
Expo Talk Panel
Sun Jul 18 05:00 PM -- 05:59 PM (PDT)
Enterprise-Strength Federated Learning: New Algorithms, New Paradigms, and a Participant-Interactive Demonstration Session
Expo Workshop
Sun Jul 18 05:00 PM -- 09:00 PM (PDT)
PaddlePaddle-based Deep Learning at Baidu
Expo Talk Panel
Sun Jul 18 07:00 PM -- 08:00 PM (PDT)
Graviti Open Datasets: A peek into the future of Open Data
Expo Demonstration
Sun Jul 18 09:00 PM -- 10:00 PM (PDT)
Explainable Entity Matching for Master Data Management
Affinity Workshop
Mon Jul 19 08:00 AM -- 05:00 PM (PDT)
LatinX in AI (LXAI) Research at ICML 2021
Tutorial
Mon Jul 19 08:00 AM -- 11:15 AM (PDT)
From ML research to ML products: A path towards building models with real-world impact
Tutorial
Mon Jul 19 08:00 AM -- 10:59 AM (PDT)
Sparsity in Deep Learning: Pruning and growth for efficient inference and training
[ Paper ]
Tutorial
Mon Jul 19 08:00 AM -- 11:00 AM (PDT) @ Virtual
Natural-XAI: Explainable AI with Natural Language Explanations
[
Slides]
Tutorial
Mon Jul 19 08:00 AM -- 11:00 AM (PDT)
Synthetic Healthcare Data Generation and Assessment: Challenges, Methods, and Impact on Machine Learning
Tutorial
Mon Jul 19 08:00 AM -- 11:00 AM (PDT) @ Virtual
Responsible AI in Industry: Practical Challenges and Lessons Learned
[
Slides]
Tutorial
Mon Jul 19 08:00 AM -- 11:05 AM (PDT) @ Virtual
Continual Learning with Deep Architectures
[
Slides]
Tutorial
Mon Jul 19 12:00 PM -- 02:50 PM (PDT)
Social Implications of Large Language Models
Tutorial
Mon Jul 19 12:00 PM -- 03:00 PM (PDT) @ Virtual
Online and non-stochastic control
[
Slides]
Tutorial
Mon Jul 19 12:00 PM -- 03:00 PM (PDT) @ Virtual
Unsupervised Learning for Reinforcement Learning
[
Slides]
Tutorial
Mon Jul 19 12:00 PM -- 03:00 PM (PDT) @ Virtual
Random Matrix Theory and ML (RMT+ML)
[
Slides]
Affinity Poster Session
Mon Jul 19 06:00 PM -- 08:00 PM (PDT)
LatinX in AI, Queer in AI, WiML - Joint Poster Session
Tutorial
Mon Jul 19 08:00 PM -- 10:45 PM (PDT) @ Virtual
Self-Attention for Computer Vision
[
Slides]
Tutorial
Mon Jul 19 08:00 PM -- 11:00 PM (PDT) @ Virtual
Privacy in learning: Basics and the interplay
[
Slides]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Attention is not all you need: pure attention loses rank doubly exponentially with depth
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Relative Positional Encoding for Transformers with Linear Complexity
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
Size-Invariant Graph Representations for Graph Classification Extrapolations
[ Paper ]
Oral
Tue Jul 20 05:00 AM -- 05:20 AM (PDT)
BORE: Bayesian Optimization by Density-Ratio Estimation
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
Consistent Nonparametric Methods for Network Assisted Covariate Estimation
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
AutoSampling: Search for Effective Data Sampling Schedules
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
Offline Contextual Bandits with Overparameterized Models
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
Reinforcement Learning with Prototypical Representations
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
Stochastic Sign Descent Methods: New Algorithms and Better Theory
[ Paper ]
Spotlight
Tue Jul 20 05:20 AM -- 05:25 AM (PDT)
A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Explainable Automated Graph Representation Learning with Hyperparameter Importance
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Dataset Dynamics via Gradient Flows in Probability Space
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
[ Paper ]
Spotlight
Tue Jul 20 05:25 AM -- 05:30 AM (PDT)
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
Muesli: Combining Improvements in Policy Optimization
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
A New Representation of Successor Features for Transfer across Dissimilar Environments
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
Exploiting structured data for learning contagious diseases under incomplete testing
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
Bias-Robust Bayesian Optimization via Dueling Bandits
[ Paper ]
Spotlight
Tue Jul 20 05:30 AM -- 05:35 AM (PDT)
Breaking the Limits of Message Passing Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
Evolving Attention with Residual Convolutions
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
Unsupervised Learning of Visual 3D Keypoints for Control
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
[ Paper ]
Spotlight
Tue Jul 20 05:35 AM -- 05:40 AM (PDT)
From Local Structures to Size Generalization in Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Large-Margin Contrastive Learning with Distance Polarization Regularizer
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Sparsifying Networks via Subdifferential Inclusion
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
On the Optimality of Batch Policy Optimization Algorithms
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Interpretable Stability Bounds for Spectral Graph Filters
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Newton Method over Networks is Fast up to the Statistical Precision
[ Paper ]
Spotlight
Tue Jul 20 05:40 AM -- 05:45 AM (PDT)
Zoo-Tuning: Adaptive Transfer from A Zoo of Models
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
Making transport more robust and interpretable by moving data through a small number of anchor points
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
Federated Learning under Arbitrary Communication Patterns
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
UnICORNN: A recurrent model for learning very long time dependencies
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
State Entropy Maximization with Random Encoders for Efficient Exploration
[ Paper ]
Spotlight
Tue Jul 20 05:45 AM -- 05:50 AM (PDT)
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
What Are Bayesian Neural Network Posteriors Really Like?
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
Principled Simplicial Neural Networks for Trajectory Prediction
[ Paper ]
Oral
Tue Jul 20 06:00 AM -- 06:20 AM (PDT)
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Voice2Series: Reprogramming Acoustic Models for Time Series Classification
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Efficient Differentiable Simulation of Articulated Bodies
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Is Space-Time Attention All You Need for Video Understanding?
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
[ Paper ]
Spotlight
Tue Jul 20 06:20 AM -- 06:25 AM (PDT)
Fundamental Tradeoffs in Distributionally Adversarial Training
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
Towards Understanding Learning in Neural Networks with Linear Teachers
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
GraphDF: A Discrete Flow Model for Molecular Graph Generation
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
A Probabilistic Approach to Neural Network Pruning
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT) @ Virtual
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
On Monotonic Linear Interpolation of Neural Network Parameters
[ Paper ]
Spotlight
Tue Jul 20 06:25 AM -- 06:30 AM (PDT)
Self-Tuning for Data-Efficient Deep Learning
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
Connecting Sphere Manifolds Hierarchically for Regularization
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
Parameter-free Locally Accelerated Conditional Gradients
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
How Framelets Enhance Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
Hierarchical VAEs Know What They Don’t Know
[ Paper ]
Spotlight
Tue Jul 20 06:30 AM -- 06:35 AM (PDT)
Distributionally Robust Optimization with Markovian Data
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
A Functional Perspective on Learning Symmetric Functions with Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Acceleration via Fractal Learning Rate Schedules
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Principal Component Hierarchy for Sparse Quadratic Programs
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Federated Continual Learning with Weighted Inter-client Transfer
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Provably Efficient Learning of Transferable Rewards
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 06:35 AM -- 06:40 AM (PDT)
Efficient Lottery Ticket Finding: Less Data is More
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
Bayesian Deep Learning via Subnetwork Inference
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
A Novel Sequential Coreset Method for Gradient Descent Algorithms
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
One-sided Frank-Wolfe algorithms for saddle problems
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
Reinforcement Learning for Cost-Aware Markov Decision Processes
[ Paper ]
Spotlight
Tue Jul 20 06:40 AM -- 06:45 AM (PDT)
Generative Video Transformer: Can Objects be the Words?
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Generative Particle Variational Inference via Estimation of Functional Gradients
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
On the Random Conjugate Kernel and Neural Tangent Kernel
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Provably Strict Generalisation Benefit for Equivariant Models
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Federated Learning of User Verification Models Without Sharing Embeddings
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation
[ Paper ]
Spotlight
Tue Jul 20 06:45 AM -- 06:50 AM (PDT)
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Not All Memories are Created Equal: Learning to Forget by Expiring
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
World Model as a Graph: Learning Latent Landmarks for Planning
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
Skill Discovery for Exploration and Planning using Deep Skill Graphs
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
OmniNet: Omnidirectional Representations from Transformers
[ Paper ]
Oral
Tue Jul 20 07:00 AM -- 07:20 AM (PDT)
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Learning Routines for Effective Off-Policy Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Learning Curves for Analysis of Deep Networks
[ Paper ]
Spotlight
Tue Jul 20 07:20 AM -- 07:25 AM (PDT)
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
Variational Data Assimilation with a Learned Inverse Observation Operator
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
PODS: Policy Optimization via Differentiable Simulation
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
A New Formalism, Method and Open Issues for Zero-Shot Coordination
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
Perceiver: General Perception with Iterative Attention
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
GLSearch: Maximum Common Subgraph Detection via Learning to Search
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
Autoencoding Under Normalization Constraints
[ Paper ]
Spotlight
Tue Jul 20 07:25 AM -- 07:30 AM (PDT)
LieTransformer: Equivariant Self-Attention for Lie Groups
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Learning and Planning in Complex Action Spaces
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Learning Intra-Batch Connections for Deep Metric Learning
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Targeted Data Acquisition for Evolving Negotiation Agents
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Synthesizer: Rethinking Self-Attention for Transformer Models
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Offline Reinforcement Learning with Pseudometric Learning
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
PixelTransformer: Sample Conditioned Signal Generation
[ Paper ]
Spotlight
Tue Jul 20 07:30 AM -- 07:35 AM (PDT)
Fast Projection Onto Convex Smooth Constraints
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Model-Based Reinforcement Learning via Latent-Space Collocation
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Decomposable Submodular Function Minimization via Maximum Flow
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Inverse Constrained Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:35 AM -- 07:40 AM (PDT)
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Multiplicative Noise and Heavy Tails in Stochastic Optimization
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Autoencoder Image Interpolation by Shaping the Latent Space
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Parallelizing Legendre Memory Unit Training
[ Paper ]
Spotlight
Tue Jul 20 07:40 AM -- 07:45 AM (PDT)
Unifying Vision-and-Language Tasks via Text Generation
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
DeepWalking Backwards: From Embeddings Back to Graphs
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
Improved Denoising Diffusion Probabilistic Models
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
Better Training using Weight-Constrained Stochastic Dynamics
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
Distributed Second Order Methods with Fast Rates and Compressed Communication
[ Paper ]
Spotlight
Tue Jul 20 07:45 AM -- 07:50 AM (PDT)
Interactive Learning from Activity Description
[ Paper ]
Affinity Workshop
Tue Jul 20 08:00 AM -- 05:00 PM (PDT)
Queer in AI Workshop
Invited Talk
Tue Jul 20 08:00 AM -- 09:00 AM (PDT)
Rethinking Drug Discovery in the Era of Digital Biology
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Acceleration via Fractal Learning Rate Schedules
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Targeted Data Acquisition for Evolving Negotiation Agents
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Perceiver: General Perception with Iterative Attention
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
MC-LSTM: Mass-Conserving LSTM
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Dueling Convex Optimization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
DeepWalking Backwards: From Embeddings Back to Graphs
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Learning and Planning in Complex Action Spaces
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Efficient Lottery Ticket Finding: Less Data is More
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Reinforcement Learning with Prototypical Representations
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
On Monotonic Linear Interpolation of Neural Network Parameters
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Deeply-Debiased Off-Policy Interval Estimation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Parallelizing Legendre Memory Unit Training
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Provably Efficient Learning of Transferable Rewards
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Leveraging Sparse Linear Layers for Debuggable Deep Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Phasic Policy Gradient
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Sparsifying Networks via Subdifferential Inclusion
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Interactive Learning from Activity Description
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Probabilistic Approach to Neural Network Pruning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Self Normalizing Flows
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Decoupling Value and Policy for Generalization in Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
From Local Structures to Size Generalization in Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
GLSearch: Maximum Common Subgraph Detection via Learning to Search
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Skill Discovery for Exploration and Planning using Deep Skill Graphs
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Better Training using Weight-Constrained Stochastic Dynamics
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Reinforcement Learning for Cost-Aware Markov Decision Processes
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Newton Method over Networks is Fast up to the Statistical Precision
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Muesli: Combining Improvements in Policy Optimization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Projection Robust Wasserstein Barycenters
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Model-Based Reinforcement Learning via Latent-Space Collocation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Inverse Constrained Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A New Representation of Successor Features for Transfer across Dissimilar Environments
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Principled Simplicial Neural Networks for Trajectory Prediction
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Efficient Differentiable Simulation of Articulated Bodies
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
BORE: Bayesian Optimization by Density-Ratio Estimation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Variational Data Assimilation with a Learned Inverse Observation Operator
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
How Framelets Enhance Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
KNAS: Green Neural Architecture Search
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
GraphDF: A Discrete Flow Model for Molecular Graph Generation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Provably Strict Generalisation Benefit for Equivariant Models
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Decomposable Submodular Function Minimization via Maximum Flow
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Winograd Algorithm for AdderNet
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Sliced Iterative Normalizing Flows
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Neural Architecture Search without Training
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Principal Component Hierarchy for Sparse Quadratic Programs
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
PixelTransformer: Sample Conditioned Signal Generation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
A Functional Perspective on Learning Symmetric Functions with Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Value Alignment Verification
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Federated Learning under Arbitrary Communication Patterns
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Large-Margin Contrastive Learning with Distance Polarization Regularizer
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Not All Memories are Created Equal: Learning to Forget by Expiring
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Multiplicative Noise and Heavy Tails in Stochastic Optimization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Connecting Sphere Manifolds Hierarchically for Regularization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Strategic Classification Made Practical
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Making transport more robust and interpretable by moving data through a small number of anchor points
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
UnICORNN: A recurrent model for learning very long time dependencies
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A New Formalism, Method and Open Issues for Zero-Shot Coordination
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Self-Tuning for Data-Efficient Deep Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
What Are Bayesian Neural Network Posteriors Really Like?
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Preferential Temporal Difference Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Unsupervised Learning of Visual 3D Keypoints for Control
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Graph Mixture Density Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Synthesizer: Rethinking Self-Attention for Transformer Models
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Intra-Batch Connections for Deep Metric Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Parameter-free Locally Accelerated Conditional Gradients
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Bounds for Open-Set Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Federated Continual Learning with Weighted Inter-client Transfer
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Distributed Second Order Methods with Fast Rates and Compressed Communication
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Autoencoding Under Normalization Constraints
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Stochastic Sign Descent Methods: New Algorithms and Better Theory
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Federated Learning of User Verification Models Without Sharing Embeddings
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Offline Contextual Bandits with Overparameterized Models
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Generative Video Transformer: Can Objects be the Words?
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Novel Sequential Coreset Method for Gradient Descent Algorithms
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Decentralized Riemannian Gradient Descent on the Stiefel Manifold
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
LieTransformer: Equivariant Self-Attention for Lie Groups
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Directional Graph Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Dataset Dynamics via Gradient Flows in Probability Space
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
E(n) Equivariant Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Curves for Analysis of Deep Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
MSA Transformer
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Grid-Functioned Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Outlier-Robust Optimal Transport
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Autoencoder Image Interpolation by Shaping the Latent Space
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
On the Random Conjugate Kernel and Neural Tangent Kernel
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Imitation by Predicting Observations
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Attention is not all you need: pure attention loses rank doubly exponentially with depth
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Bias-Robust Bayesian Optimization via Dueling Bandits
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
One-sided Frank-Wolfe algorithms for saddle problems
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
OmniNet: Omnidirectional Representations from Transformers
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Is Space-Time Attention All You Need for Video Understanding?
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Thinking Like Transformers
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Breaking the Limits of Message Passing Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Low-Rank Sinkhorn Factorization
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
AutoSampling: Search for Effective Data Sampling Schedules
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Consistent Nonparametric Methods for Network Assisted Covariate Estimation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
PODS: Policy Optimization via Differentiable Simulation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Vector Quantized Models for Planning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Unifying Vision-and-Language Tasks via Text Generation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
PID Accelerated Value Iteration Algorithm
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Generative Particle Variational Inference via Estimation of Functional Gradients
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Generative Adversarial Transformers
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Relative Positional Encoding for Transformers with Linear Complexity
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Hierarchical VAEs Know What They Don’t Know
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Riemannian Convex Potential Maps
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Bayesian Deep Learning via Subnetwork Inference
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Learning Routines for Effective Off-Policy Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Exploiting structured data for learning contagious diseases under incomplete testing
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Size-Invariant Graph Representations for Graph Classification Extrapolations
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Offline Reinforcement Learning with Pseudometric Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Fast Projection Onto Convex Smooth Constraints
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Neural Symbolic Regression that scales
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Improved Denoising Diffusion Probabilistic Models
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
World Model as a Graph: Learning Latent Landmarks for Planning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
On the Optimality of Batch Policy Optimization Algorithms
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Zoo-Tuning: Adaptive Transfer from A Zoo of Models
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Evolving Attention with Residual Convolutions
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Momentum Residual Neural Networks
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
State Entropy Maximization with Random Encoders for Efficient Exploration
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Towards Understanding Learning in Neural Networks with Linear Teachers
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Optimal Complexity in Decentralized Training
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Deep kernel processes
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Fundamental Tradeoffs in Distributionally Adversarial Training
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Explainable Automated Graph Representation Learning with Hyperparameter Importance
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Distributionally Robust Optimization with Markovian Data
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Task Informed Abstractions
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
Interpretable Stability Bounds for Spectral Graph Filters
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
Poster
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
Session
Tue Jul 20 09:00 AM -- 11:00 AM (PDT)
Poster Session 1
Town Hall
Tue Jul 20 11:00 AM -- 12:00 PM (PDT)
Town Hall
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
A Tale of Two Efficient and Informative Negative Sampling Distributions
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
Characterizing Structural Regularities of Labeled Data in Overparameterized Models
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
On the price of explainability for some clustering problems
[ Paper ]
Oral
Tue Jul 20 05:00 PM -- 05:20 PM (PDT)
CATE: Computation-aware Neural Architecture Encoding with Transformers
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Stabilizing Equilibrium Models by Jacobian Regularization
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Safe Reinforcement Learning with Linear Function Approximation
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Instance Specific Approximations for Submodular Maximization
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Re-understanding Finite-State Representations of Recurrent Policy Networks
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Differentiable Spatial Planning using Transformers
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
[ Paper ]
Spotlight
Tue Jul 20 05:20 PM -- 05:25 PM (PDT)
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Quantization Algorithms for Random Fourier Features
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Adapting to Delays and Data in Adversarial Multi-Armed Bandits
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Towards Domain-Agnostic Contrastive Learning
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
On the Predictability of Pruning Across Scales
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Convex Regularization in Monte-Carlo Tree Search
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Soft then Hard: Rethinking the Quantization in Neural Image Compression
[ Paper ]
Spotlight
Tue Jul 20 05:25 PM -- 05:30 PM (PDT)
Emergent Social Learning via Multi-agent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Improved Contrastive Divergence Training of Energy-Based Models
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Signatured Deep Fictitious Play for Mean Field Games with Common Noise
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Joining datasets via data augmentation in the label space for neural networks
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Structured Convolutional Kernel Networks for Airline Crew Scheduling
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
[ Paper ]
Spotlight
Tue Jul 20 05:30 PM -- 05:35 PM (PDT)
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Deep Generative Learning via Schrödinger Bridge
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Multi-Task Reinforcement Learning with Context-based Representations
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Equivariant message passing for the prediction of tensorial properties and molecular spectra
[ Paper ]
Spotlight
Tue Jul 20 05:35 PM -- 05:40 PM (PDT)
Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
Heterogeneity for the Win: One-Shot Federated Clustering
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
High Confidence Generalization for Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
[ Paper ]
Spotlight
Tue Jul 20 05:40 PM -- 05:45 PM (PDT)
Trajectory Diversity for Zero-Shot Coordination
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Discovering symbolic policies with deep reinforcement learning
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
LARNet: Lie Algebra Residual Network for Face Recognition
[ Paper ]
Spotlight
Tue Jul 20 05:45 PM -- 05:50 PM (PDT)
Poolingformer: Long Document Modeling with Pooling Attention
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
The Power of Adaptivity for Stochastic Submodular Cover
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Decoupling Value and Policy for Generalization in Reinforcement Learning
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
A Wasserstein Minimax Framework for Mixed Linear Regression
In
Algorithms 1
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Network Inference and Influence Maximization from Samples
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
[ Paper ]
Oral
Tue Jul 20 06:00 PM -- 06:20 PM (PDT)
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
EfficientNetV2: Smaller Models and Faster Training
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
An Identifiable Double VAE For Disentangled Representations
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
Weight-covariance alignment for adversarially robust neural networks
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:20 PM -- 06:25 PM (PDT)
Regularized Submodular Maximization at Scale
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
Keyframe-Focused Visual Imitation Learning
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
[ Paper ]
Spotlight
Tue Jul 20 06:25 PM -- 06:30 PM (PDT)
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
Connecting Interpretability and Robustness in Decision Trees through Separation
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
GMAC: A Distributional Perspective on Actor-Critic Framework
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
LAMDA: Label Matching Deep Domain Adaptation
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
Learning While Playing in Mean-Field Games: Convergence and Optimality
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
On Characterizing GAN Convergence Through Proximal Duality Gap
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
Learning and Planning in Average-Reward Markov Decision Processes
[ Paper ]
Spotlight
Tue Jul 20 06:30 PM -- 06:35 PM (PDT)
Communication-Efficient Distributed SVD via Local Power Iterations
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Temporally Correlated Task Scheduling for Sequence Learning
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
[ Paper ]
Spotlight
Tue Jul 20 06:35 PM -- 06:40 PM (PDT)
Scalable Normalizing Flows for Permutation Invariant Densities
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Information Obfuscation of Graph Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Policy Gradient Bayesian Robust Optimization for Imitation Learning
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
[ Paper ]
Spotlight
Tue Jul 20 06:40 PM -- 06:45 PM (PDT)
Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:45 PM -- 06:50 PM (PDT)
BASGD: Buffered Asynchronous SGD for Byzantine Learning
[ Paper ]
Spotlight
Tue Jul 20 06:45 PM -- 06:50 PM (PDT)
Leveraging Language to Learn Program Abstractions and Search Heuristics
In
Algorithms 1
[ Paper ]
Spotlight
Tue Jul 20 06:45 PM -- 06:50 PM (PDT)
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
[ Paper ]
Spotlight
Tue Jul 20 06:45 PM -- 06:50 PM (PDT)
Emphatic Algorithms for Deep Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 06:45 PM -- 06:50 PM (PDT)
Reinforcement Learning of Implicit and Explicit Control Flow Instructions
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Inverse Decision Modeling: Learning Interpretable Representations of Behavior
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
AlphaNet: Improved Training of Supernets with Alpha-Divergence
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Just Train Twice: Improving Group Robustness without Training Group Information
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Out-of-Distribution Generalization via Risk Extrapolation (REx)
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
[ Paper ]
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
Hyperparameter Selection for Imitation Learning
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
What Makes for End-to-End Object Detection?
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Communication-Efficient Distributed Optimization with Quantized Preconditioners
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Catformer: Designing Stable Transformers via Sensitivity Analysis
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Oblivious Sketching-based Central Path Method for Linear Programming
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
On Proximal Policy Optimization's Heavy-tailed Gradients
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Learning to Weight Imperfect Demonstrations
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
A Receptor Skeleton for Capsule Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Monotonic Robust Policy Optimization with Model Discrepancy
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
On Explainability of Graph Neural Networks via Subgraph Explorations
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Explore Visual Concept Formation for Image Classification
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Training Graph Neural Networks with 1000 Layers
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
Neural Rough Differential Equations for Long Time Series
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
Is Pessimism Provably Efficient for Offline RL?
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
Generalizable Episodic Memory for Deep Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
Compositional Video Synthesis with Action Graphs
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Representation Matters: Offline Pretraining for Sequential Decision Making
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
High-Performance Large-Scale Image Recognition Without Normalization
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Neural Pharmacodynamic State Space Modeling
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
RRL: Resnet as representation for Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Three Operator Splitting with a Nonconvex Loss Function
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Density Constrained Reinforcement Learning
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
On a Combination of Alternating Minimization and Nesterov's Momentum
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Lipschitz normalization for self-attention layers with application to graph neural networks
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Ditto: Fair and Robust Federated Learning Through Personalization
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Reinforcement Learning Under Moral Uncertainty
[ Paper ]
Invited Talk
Tue Jul 20 08:00 PM -- 09:00 PM (PDT)
Cryospheric Science and Emergence of Machine Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
On Estimation in Latent Variable Models
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Oblivious Sketching-based Central Path Method for Linear Programming
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Re-understanding Finite-State Representations of Recurrent Policy Networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
The Power of Adaptivity for Stochastic Submodular Cover
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Tale of Two Efficient and Informative Negative Sampling Distributions
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Differentiable Spatial Planning using Transformers
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Generalizable Episodic Memory for Deep Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Density Constrained Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Catformer: Designing Stable Transformers via Sensitivity Analysis
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
High Confidence Generalization for Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Taylor Expansion of Discount Factors
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Online Graph Dictionary Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
CATE: Computation-aware Neural Architecture Encoding with Transformers
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Reinforcement Learning Under Moral Uncertainty
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Safe Reinforcement Learning with Linear Function Approximation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Multi-Task Reinforcement Learning with Context-based Representations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Just Train Twice: Improving Group Robustness without Training Group Information
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
BASGD: Buffered Asynchronous SGD for Byzantine Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Learning and Planning in Average-Reward Markov Decision Processes
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
On Proximal Policy Optimization's Heavy-tailed Gradients
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Stochastic Iterative Graph Matching
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Improved Contrastive Divergence Training of Energy-Based Models
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Instance Specific Approximations for Submodular Maximization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
EfficientNetV2: Smaller Models and Faster Training
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Moreau-Yosida $f$-divergences
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Is Pessimism Provably Efficient for Offline RL?
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Emergent Social Learning via Multi-agent Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Accurate Post Training Quantization With Small Calibration Sets
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Signatured Deep Fictitious Play for Mean Field Games with Common Noise
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Lipschitz normalization for self-attention layers with application to graph neural networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Data Augmentation for Meta-Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Keyframe-Focused Visual Imitation Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Neural Rough Differential Equations for Long Time Series
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
LARNet: Lie Algebra Residual Network for Face Recognition
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Training Graph Neural Networks with 1000 Layers
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
The Emergence of Individuality
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Deep Generative Learning via Schrödinger Bridge
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Discovering symbolic policies with deep reinforcement learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Equivariant message passing for the prediction of tensorial properties and molecular spectra
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Structured Convolutional Kernel Networks for Airline Crew Scheduling
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Ditto: Fair and Robust Federated Learning Through Personalization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Learning to Weight Imperfect Demonstrations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Inverse Decision Modeling: Learning Interpretable Representations of Behavior
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Bayesian Optimization over Hybrid Spaces
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Receptor Skeleton for Capsule Neural Networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Learning While Playing in Mean-Field Games: Convergence and Optimality
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
On Characterizing GAN Convergence Through Proximal Duality Gap
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Leveraging Language to Learn Program Abstractions and Search Heuristics
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Generating images with sparse representations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
On the price of explainability for some clustering problems
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Soft then Hard: Rethinking the Quantization in Neural Image Compression
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
RRL: Resnet as representation for Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Compositional Video Synthesis with Action Graphs
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Emphatic Algorithms for Deep Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Temporally Correlated Task Scheduling for Sequence Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Scalable Normalizing Flows for Permutation Invariant Densities
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
GMAC: A Distributional Perspective on Actor-Critic Framework
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Network Inference and Influence Maximization from Samples
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
On Explainability of Graph Neural Networks via Subgraph Explorations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
What Makes for End-to-End Object Detection?
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Regularized Submodular Maximization at Scale
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Heterogeneity for the Win: One-Shot Federated Clustering
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Characterizing Structural Regularities of Labeled Data in Overparameterized Models
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Federated Composite Optimization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Information Obfuscation of Graph Neural Networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Light RUMs
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
LAMDA: Label Matching Deep Domain Adaptation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
AutoAttend: Automated Attention Representation Search
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Robust Asymmetric Learning in POMDPs
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
On a Combination of Alternating Minimization and Nesterov's Momentum
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
A Wasserstein Minimax Framework for Mixed Linear Regression
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Partially Observed Exchangeable Modeling
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Connecting Interpretability and Robustness in Decision Trees through Separation
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Convex Regularization in Monte-Carlo Tree Search
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Communication-Efficient Distributed Optimization with Quantized Preconditioners
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Representation Matters: Offline Pretraining for Sequential Decision Making
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Communication-Efficient Distributed SVD via Local Power Iterations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Joining datasets via data augmentation in the label space for neural networks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
High-Performance Large-Scale Image Recognition Without Normalization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Poolingformer: Long Document Modeling with Pooling Attention
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Explore Visual Concept Formation for Image Classification
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
On the Predictability of Pruning Across Scales
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Trajectory Diversity for Zero-Shot Coordination
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Stabilizing Equilibrium Models by Jacobian Regularization
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
The Heavy-Tail Phenomenon in SGD
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Policy Gradient Bayesian Robust Optimization for Imitation Learning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
An Identifiable Double VAE For Disentangled Representations
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Monotonic Robust Policy Optimization with Model Discrepancy
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Three Operator Splitting with a Nonconvex Loss Function
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
Prioritized Level Replay
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Out-of-Distribution Generalization via Risk Extrapolation (REx)
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Reinforcement Learning of Implicit and Explicit Control Flow Instructions
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Few-Shot Neural Architecture Search
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT)
Quantization Algorithms for Random Fourier Features
Poster
Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
[
Slides]