Ambuj Tewari

Affiliations

University of Michigan

papers

160

total citations

papers (15)

On the Equivalence between Online and Private Learnability beyond Binary Classification

NEURIPS 2020arXiv

citations

Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

NEURIPS 2020arXiv

citations

Variational Inference with Coverage Guarantees in Simulation-Based Inference

ICML 2024arXiv

citations

Adaptive Sampling for Discovery

NEURIPS 2022arXiv

citations

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs

ICML 2024arXiv

citations

On Proper Learnability between Average- and Worst-case Robustness

NEURIPS 2023arXiv

citations

Online Agnostic Multiclass Boosting

NEURIPS 2022arXiv

citations

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

ICLR 2024arXiv

citations

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

ICML 2025arXiv

citations

On the Learnability of Multilabel Ranking

NEURIPS 2023arXiv

citations

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

NEURIPS 2025arXiv

citations

Leveraging Offline Data in Linear Latent Contextual Bandits

ICML 2025arXiv

citations

Ambuj Tewari

Affiliations

papers (15)

Causal Bandits with Unknown Graph Structure

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search

Representation Learning Beyond Linear Prediction Functions

On the Equivalence between Online and Private Learnability beyond Binary Classification

Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

Variational Inference with Coverage Guarantees in Simulation-Based Inference

Adaptive Sampling for Discovery

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs

On Proper Learnability between Average- and Worst-case Robustness

Online Agnostic Multiclass Boosting

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

On the Learnability of Multilabel Ranking

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

Leveraging Offline Data in Linear Latent Contextual Bandits

papers (15)

Causal Bandits with Unknown Graph Structure

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search

Representation Learning Beyond Linear Prediction Functions

On the Equivalence between Online and Private Learnability beyond Binary Classification

Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

Variational Inference with Coverage Guarantees in Simulation-Based Inference

Adaptive Sampling for Discovery

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs

On Proper Learnability between Average- and Worst-case Robustness

Online Agnostic Multiclass Boosting

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

On the Learnability of Multilabel Ranking

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

Leveraging Offline Data in Linear Latent Contextual Bandits