Yu Bai

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining.

[BibT_eX]

[DOI]

Licong Lin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning?

[BibT_eX]

[DOI]

Lei Zhao

Mengdi Wang

CoRR, 2023

What can a Single Attention Layer Learn? A Study Through the Random Features Lens.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Lower Bounds for Learning in Revealing POMDPs.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Improved Online Conformal Prediction via Strongly Adaptive Online Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

The Role of Coverage in Online Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms.

[BibT_eX]

[DOI]

Fan Chen

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning Rationalizable Equilibria in Multiplayer Games.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning.

[BibT_eX]

[DOI]

Fan Chen

CoRR, 2022

Efficient Φ-Regret Minimization in Extensive-Form Games via Online Mirror Descent.

[BibT_eX]

[DOI]

CoRR, 2022

Local calibration: metrics and recalibration.

[BibT_eX]

[DOI]

Proceedings of the Uncertainty in Artificial Intelligence, 2022

Policy Optimization for Markov Games: Unified Framework and Faster Convergence.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games.

[BibT_eX]

[DOI]

Ziang Song

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials.

[BibT_eX]

[DOI]

Eshaan Nichani

Jason D. Lee

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Near-Optimal Learning of Extensive-Form Games with Imperfect Information.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?

[BibT_eX]

[DOI]

Ziang Song

Proceedings of the Tenth International Conference on Learning Representations, 2022

Efficient and Differentiable Conformal Prediction with General Function Classes.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Conformal Predictor for Improving Zero-Shot Text Classification Efficiency.

[BibT_eX]

[DOI]

Prafulla Kumar Choubey

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021

Localized Calibration: Metrics and Recalibration.

[BibT_eX]

[DOI]

CoRR, 2021

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction.

[BibT_eX]

[DOI]

Ming Yin

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Understanding the Under-Coverage Bias in Uncertainty Estimation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models.

[BibT_eX]

[DOI]

Zitong Yang

Proceedings of the 38th International Conference on Machine Learning, 2021

A Sharp Analysis of Model-based Reinforcement Learning with Self-Play.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

How Important is the Train-Validation Split in Meta-Learning?

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning.

[BibT_eX]

[DOI]

Ming Yin

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning.

[BibT_eX]

[DOI]

Ming Yin

CoRR, 2020

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width.

[BibT_eX]

[DOI]

CoRR, 2020

Towards Understanding Hierarchical Learning: Benefits of Neural Representations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Near-Optimal Reinforcement Learning with Self-Play.

[BibT_eX]

[DOI]

Chi Jin

Tiancheng Yu

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Provable Self-Play Algorithms for Competitive Reinforcement Learning.

[BibT_eX]

[DOI]

Chi Jin

Proceedings of the 37th International Conference on Machine Learning, 2020

Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks.

[BibT_eX]

[DOI]

Jason D. Lee

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs.

[BibT_eX]

[DOI]

John C. Duchi

CoRR, 2019

Provably Efficient Q-Learning with Low Switching Cost.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

ProxQuant: Quantized Neural Networks via Proximal Operators.

[BibT_eX]

[DOI]

Edo Liberty

Proceedings of the 7th International Conference on Learning Representations, 2019

Approximability of Discriminators Implies Diversity in GANs.

[BibT_eX]

[DOI]

Tengyu Ma

Andrej Risteski

Proceedings of the 7th International Conference on Learning Representations, 2019

Subgradient Descent Learns Orthogonal Dictionaries.

[BibT_eX]

[DOI]