Toggle Poster Visibility
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
TempoRL: Learning When to Act
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
What does LIME really see in images?
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Approximate Group Fairness for Clustering
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
How to Learn when Data Reacts to Your Model: Performative Gradient Descent
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
On Energy-Based Models with Overparametrized Shallow Neural Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Dynamic Game Theoretic Neural Optimizer
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Ensemble Bootstrapping for Q-Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
A Regret Minimization Approach to Iterative Learning Control
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Faster Kernel Matrix Algebra via Density Estimation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning from Nested Data with Ornstein Auto-Encoders
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Elastic Graph Neural Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Composing Normalizing Flows for Inverse Problems
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Online A-Optimal Design and Active Linear Regression
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Kernel Stein Discrepancy Descent
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Data-efficient Hindsight Off-policy Option Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Meta-learning Hyperparameter Performance Prediction with Neural Processes
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Best Model Identification: A Rested Bandit Formulation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Estimating $\alpha$-Rank from A Few Entries with Low Rank Matrix Completion
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Generalised Lipschitz Regularisation Equals Distributional Robustness
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Instabilities of Offline RL with Pre-Trained Neural Representation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Multi-group Agnostic PAC Learnability
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Deep Continuous Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Near-Optimal Confidence Sequences for Bounded Random Variables
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
PAC-Learning for Strategic Classification
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
How could Neural Networks understand Programs?
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Incentivizing Compliance with Algorithmic Instruments
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
A statistical perspective on distillation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Guided Exploration with Proximal Policy Optimization using a Single Demonstration
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Model-Free and Model-Based Policy Evaluation when Causality is Uncertain
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
An exact solver for the Weston-Watkins SVM subproblem
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Relative Deviation Margin Bounds
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Exponentially Many Local Minima in Quantum Neural Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Instance-Optimal Compressed Sensing via Posterior Sampling
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Training Data Subset Selection for Regression with Controlled Generalization Error
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
The Lipschitz Constant of Self-Attention
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
How Do Adam and Training Strategies Help BNNs Optimization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Continuous-time Model-based Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Off-Belief Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Unsupervised Skill Discovery with Bottleneck Option Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Homomorphic Sensing: Sparsity and Noise
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Distributed Nystr\"{o}m Kernel Learning with Communications
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Approximating a Distribution Using Weight Queries
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
SMG: A Shuffling Gradient-Based Method with Momentum
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Multiplying Matrices Without Multiplying
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Nonparametric Hamiltonian Monte Carlo
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Bayesian Optimistic Optimisation with Exponentially Decaying Regret
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Narrow Margins: Classification, Margins and Fat Tails
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Reward Identification in Inverse Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Dichotomous Optimistic Search to Quantify Human Perception
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Adversarial Option-Aware Hierarchical Imitation Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
APS: Active Pretraining with Successor Features
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Functional Space Analysis of Local GAN Convergence
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Deciding What to Learn: A Rate-Distortion Approach
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Cross-domain Imitation from Observations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Continuous Coordination As a Realistic Scenario for Lifelong Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Representational aspects of depth and conditioning in normalizing flows
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
High-dimensional Experimental Design and Kernel Bandits
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
The Logical Options Framework
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Self-Paced Context Evaluation for Contextual Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Spectral vertex sparsifiers and pair-wise spanners over distributed graphs
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Near Optimal Reward-Free Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning in Nonzero-Sum Stochastic Games with Potentials
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
A Nullspace Property for Subspace-Preserving Recovery
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Towards Rigorous Interpretations: a Formalisation of Feature Attribution
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Modelling Behavioural Diversity for Learning in Open-Ended Games
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Active Deep Probabilistic Subsampling
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Active Feature Acquisition with Generative Surrogate Models
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning from Biased Data: A Semi-Parametric Approach
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Kernel Continual Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Optimizing persistent homology based functions
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
AGENT: A Benchmark for Core Psychological Reasoning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
ChaCha for Online AutoML
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Post-selection inference with HSIC-Lasso
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Fairness and Bias in Online Selection
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Revealing the Structure of Deep Neural Networks via Convex Duality
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Uncertainty Principles of Encoding GANs
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Megaverse: Simulating Embodied Agents at One Million Experiences per Second
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning from Noisy Labels with No Change to the Training Process
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Joint Online Learning and Decision-making via Dual Mirror Descent
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Learning from History for Byzantine Robust Optimization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Measuring Robustness in Deep Learning Based Compressive Sensing
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Tractable structured natural-gradient descent using local parameterizations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Characterizing the Gap Between Actor-Critic and Policy Gradient
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
MARINA: Faster Non-Convex Distributed Learning with Compression
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Parametric Graph for Unimodal Ranking Bandit
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
No-regret Algorithms for Capturing Events in Poisson Point Processes
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Estimation and Quantization of Expected Persistence Diagrams
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Follow-the-Regularized-Leader Routes to Chaos in Routing Games
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Prior Image-Constrained Reconstruction using Style-Based Generative Models
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Bilevel Optimization: Convergence Analysis and Enhanced Design
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Collaborative Bayesian Optimization with Fair Regret
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
State Relevance for Off-Policy Evaluation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Value Iteration in Continuous Actions, States and Time
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Reserve Price Optimization for First Price Auctions in Display Advertising
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Robust Inference for High-Dimensional Linear Models via Residual Randomization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
XOR-CD: Linearly Convergent Constrained Structure Generation
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning to Price Against a Moving Target
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Bilinear Classes: A Structural Framework for Provable Generalization in RL
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Batch Value-function Approximation with Only Realizability
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Path Planning using Neural A* Search
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Large-Scale Multi-Agent Deep FBSDEs
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Learning Stochastic Behaviour from Aggregate Data
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Variance Reduced Training with Stratified Sampling for Forecasting Models
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Selecting Data Augmentation for Simulating Interventions
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Principled Exploration via Optimistic Bootstrapping and Backward Induction
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Align, then memorise: the dynamics of learning with feedback alignment
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Inferring serial correlation with dynamic backgrounds
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT)
Necessary and sufficient conditions for causal feature selection in time series with latent common causes
Poster
Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network