Tianhao Wang

Affiliations

University of California, San Diego

papers

372

total citations

papers (14)

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

NEURIPS 2021arXiv

172

citations

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

NEURIPS 2021arXiv

citations

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

NEURIPS 2022arXiv

citations

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent

NEURIPS 2022arXiv

citations

Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets

NEURIPS 2022arXiv

citations

Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function

ICLR 2025arXiv

citations

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

ICLR 2025

citations

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay

NEURIPS 2022

citations

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

NEURIPS 2023

citations

Backdoor Attacks via Machine Unlearning

AAAI 2024arXiv

citations

Tianhao Wang

Affiliations

papers (14)

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent

Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets

Towards Certified Unlearning for Deep Neural Networks

Structured Preconditioners in Adaptive Optimization: A Unified Analysis

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

Backdoor Attacks via Machine Unlearning

papers (14)

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent

Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets

Towards Certified Unlearning for Deep Neural Networks

Structured Preconditioners in Adaptive Optimization: A Unified Analysis

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

Backdoor Attacks via Machine Unlearning