Toggle Poster Visibility
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Deep Learning for Functional Data Analysis with Adaptive Basis Layers
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Dissecting Supervised Constrastive Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Optimal Off-Policy Evaluation from Multiple Logging Policies
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
A Theory of Label Propagation for Subpopulation Shift
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Selfish Sparse RNN Training
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Discriminative Complementary-Label Learning with Weighted Loss
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Learning Deep Neural Networks under Agnostic Corrupted Supervision
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Detection of Signal in the Spiked Rectangular Models
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
RATT: Leveraging Unlabeled Data to Guarantee Generalization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Adapting to misspecification in contextual bandits with offline regression oracles
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Task-Optimal Exploration in Linear Dynamical Systems
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Finding Relevant Information via a Discrete Fourier Expansion
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
On Variational Inference in Biclustering Models
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
SpreadsheetCoder: Formula Prediction from Semi-structured Context
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Compressed Maximum Likelihood
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Policy Analysis using Synthetic Controls in Continuous-Time
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
A large-scale benchmark for few-shot program induction and synthesis
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Regularized Online Allocation Problems: Fairness and Beyond
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Neural SDEs as Infinite-Dimensional GANs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Learning Generalized Intersection Over Union for Dense Pixelwise Prediction
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Latent Programmer: Discrete Latent Codes for Program Synthesis
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Toward Better Generalization Bounds with Locally Elastic Stability
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Optimizing Black-box Metrics with Iterative Example Weighting
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Mandoline: Model Evaluation under Distribution Shift
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Provably Correct Optimization and Exploration with Non-linear Policies
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Cyclically Equivariant Neural Decoders for Cyclic Codes
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Deep Coherent Exploration for Continuous Control
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
A Differentiable Point Process with Its Application to Spiking Neural Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Classification with Rejection Based on Cost-sensitive Classification
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Online Unrelated Machine Load Balancing with Predictions Revisited
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
An Information-Geometric Distance on the Space of Tasks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Analysis of stochastic Lanczos quadrature for spectrum approximation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Multi-Receiver Online Bayesian Persuasion
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Training Recurrent Neural Networks via Forward Propagation Through Time
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Dropout: Explicit Forms and Capacity Control
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Pure Exploration and Regret Minimization in Matching Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Contrastive Learning Inverts the Data Generating Process
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Alternative Microfoundations for Strategic Classification
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Interpreting and Disentangling Feature Components of Various Complexity from DNNs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
12-Lead ECG Reconstruction via Koopman Operators
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
DORO: Distributional and Outlier Robust Optimization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Safe Reinforcement Learning Using Advantage-Based Intervention
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Train simultaneously, generalize better: Stability of gradient-based minimax learners
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Best Arm Identification in Graphical Bilinear Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
A Distribution-dependent Analysis of Meta Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Deep Latent Graph Matching
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Near-Optimal Linear Regression under Distribution Shift
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Beyond $log^2(T)$ regret for decentralized bandits in matching markets
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Lower-Bounded Proper Losses for Weakly Supervised Classification
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Probabilistic Programs with Stochastic Conditioning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Asymmetric Loss Functions for Learning with Noisy Labels
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
UCB Momentum Q-learning: Correcting the bias without forgetting
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Approximation Theory Based Methods for RKHS Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Fast active learning for pure exploration in reinforcement learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Optimal Streaming Algorithms for Multi-Armed Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Learning Optimal Auctions with Correlated Valuations from Samples
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Asymptotics of Ridge Regression in Convolutional Models
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Versatile Verification of Tree Ensembles
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Randomized Exploration in Reinforcement Learning with General Value Function Approximation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Trees with Attention for Set Prediction Tasks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
An Integer Linear Programming Framework for Mining Constraints from Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Sparsity-Agnostic Lasso Bandit
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Diffusion Source Identification on Networks with Statistical Confidence
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Break-It-Fix-It: Unsupervised Learning for Program Repair
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
A Novel Method to Solve Neural Knapsack Problems
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Label Distribution Learning Machine
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Gaussian Process-Based Real-Time Learning for Safety Critical Applications
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Making Paper Reviewing Robust to Bid Manipulation Attacks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Cumulants of Hawkes Processes are Robust to Observation Noise
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Multi-Dimensional Classification via Sparse Label Encoding
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
On Robust Mean Estimation under Coordinate-level Corruption
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Scaling Properties of Deep Residual Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Learning Gradient Fields for Molecular Conformation Generation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
ACE: Explaining cluster from an adversarial perspective
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Confidence-Budget Matching for Sequential Budgeted Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Segmenting Hybrid Trajectories using Latent ODEs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Dynamic Planning and Learning under Recovering Rewards
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Consistent regression when oblivious outliers overwhelm
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Approximation Theory of Convolutional Architectures for Time Series Modelling
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Improved OOD Generalization via Adversarial Training and Pretraing
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Combinatorial Blocking Bandits with Stochastic Delays
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Conformal prediction interval for dynamic time-series
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Adversarial Dueling Bandits
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Understanding self-supervised learning dynamics without contrastive pairs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Top-k eXtreme Contextual Bandits with Arm Hierarchy
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Robust Policy Gradient against Strong Data Corruption
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Robust Pure Exploration in Linear Bandits with Limited Budget
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Towards Distraction-Robust Active Visual Tracking
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Model Performance Scaling with Multiple Data Sources
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Online Learning in Unknown Markov Games
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
DriftSurf: Stable-State / Reactive-State Learning under Concept Drift
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Heterogeneous Risk Minimization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
How Important is the Train-Validation Split in Meta-Learning?
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Consensus Control for Decentralized Deep Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Multidimensional Scaling: Approximation and Complexity
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Towards Tight Bounds on the Sample Complexity of Average-reward MDPs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Dynamic Balancing for Model Selection in Bandits and RL
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
A Precise Performance Analysis of Support Vector Regression
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
HyperHyperNetwork for the Design of Antenna Arrays
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Implicit rate-constrained optimization of non-decomposable objectives
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Leveraging Non-uniformity in First-order Non-convex Optimization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Solving Inverse Problems with a Flow-based Noise Model
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
On the Inherent Regularization Effects of Noise Injection During Training
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Sample Complexity of Robust Linear Classification on Separated Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Provable Meta-Learning of Linear Representations
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Provably Efficient Algorithms for Multi-Objective Competitive RL
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Robust Unsupervised Learning via L-statistic Minimization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
The Impact of Record Linkage on Learning from Feature Partitioned Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Outside the Echo Chamber: Optimizing the Performative Risk
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
MOTS: Minimax Optimal Thompson Sampling
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Interaction-Grounded Learning
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Event Outlier Detection in Continuous Time
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Understanding Noise Injection in GANs
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Learning by Turning: Neural Architecture Aware Optimisation
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Incentivized Bandit Learning with Self-Reinforcing User Preferences
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Quantile Bandits for Best Arms Identification
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Breaking the Deadly Triad with a Target Network
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
AdaXpert: Adapting Neural Architecture for Growing Data
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual
Near-Optimal Representation Learning for Linear Bandits and Linear RL
Poster
Wed Jul 21 09:00 PM -- 11:00 PM (PDT)
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL