Chi Jin

CoRR, 2024

2023

Provably Efficient Reinforcement Learning with Linear Function Approximation.

[BibT_eX]

[DOI]

Math. Oper. Res., August, 2023

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning.

[BibT_eX]

[DOI]

Zihan Ding

CoRR, 2023

Is RLHF More Difficult than Standard RL?

[BibT_eX]

[DOI]

Yuanhao Wang

CoRR, 2023

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference.

[BibT_eX]

[DOI]

CoRR, 2023

Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making.

[BibT_eX]

[DOI]

Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL.

[BibT_eX]

[DOI]

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

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method.

[BibT_eX]

[DOI]

Ahmed Khaled

Konstantin Mishchenko

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

Is RLHF More Difficult than Standard RL? A Theoretical Perspective.

[BibT_eX]

[DOI]

Yuanhao Wang

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

Efficient displacement convex optimization with particle gradient descent.

[BibT_eX]

[DOI]

Hadi Daneshmand

Jason D. Lee

Proceedings of the International Conference on Machine Learning, 2023

Representation Learning for Low-rank General-sum Markov Games.

[BibT_eX]

[DOI]

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

Faster federated optimization under second-order similarity.

[BibT_eX]

[DOI]

Ahmed Khaled

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

Representation Learning for General-sum Low-rank Markov Games.

[BibT_eX]

[DOI]

CoRR, 2022

A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games.

[BibT_eX]

[DOI]

Csaba Szepesvári

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

A Simple Reward-free Approach to Constrained Reinforcement Learning.

[BibT_eX]

[DOI]

Sobhan Miryoosefi

Proceedings of the International Conference on Machine Learning, 2022

Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits.

[BibT_eX]

[DOI]

Yuanhao Wang

Proceedings of the International Conference on Machine Learning, 2022

The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces.

[BibT_eX]

[DOI]

Tiancheng Yu

Proceedings of the International Conference on Machine Learning, 2022

Provable Reinforcement Learning with a Short-Term Memory.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Minimax Optimization with Smooth Algorithmic Adversaries.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

When Is Partially Observable Reinforcement Learning Not Scary?

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points.

[BibT_eX]

[DOI]

J. ACM, 2021

V-Learning - A Simple, Efficient, Decentralized Algorithm for Multiagent RL.

[BibT_eX]

[DOI]

CoRR, 2021

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms.

[BibT_eX]

[DOI]

Sobhan Miryoosefi

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

Provable Meta-Learning of Linear Representations.

[BibT_eX]

[DOI]

Nilesh Tripuraneni

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

Provable Rich Observation Reinforcement Learning with Combinatorial Latent States.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network.

[BibT_eX]

[DOI]

Mo Zhou

Rong Ge

Proceedings of the Conference on Learning Theory, 2021

2020

Bridging Exploration and General Function Approximation in Reinforcement Learning: Provably Efficient Kernel and Neural Value Iterations.

[BibT_eX]

[DOI]

CoRR, 2020

Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations.

[BibT_eX]

[DOI]

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

On the Theory of Transfer Learning: The Importance of Task Diversity.

[BibT_eX]

[DOI]

Nilesh Tripuraneni

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

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs.

[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]

Yu Bai

Tiancheng Yu

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

On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems.

[BibT_eX]

[DOI]

Tianyi Lin

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

What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?

[BibT_eX]

[DOI]

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

Reward-Free Exploration for Reinforcement Learning.

[BibT_eX]

[DOI]

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

Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition.

[BibT_eX]

[DOI]

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

Provably Efficient Exploration in Policy Optimization.

[BibT_eX]

[DOI]

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

Provable Self-Play Algorithms for Competitive Reinforcement Learning.

[BibT_eX]

[DOI]

Yu Bai

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

Near-Optimal Algorithms for Minimax Optimization.

[BibT_eX]

[DOI]

Tianyi Lin

Proceedings of the Conference on Learning Theory, 2020

2019

Machine Learning: Why Do Simple Algorithms Work So Well?

[BibT_eX]

[DOI]

PhD thesis, 2019

Stochastic Gradient Descent Escapes Saddle Points Efficiently.

[BibT_eX]

[DOI]

CoRR, 2019

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm.

[BibT_eX]

[DOI]

CoRR, 2019

Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal.

[BibT_eX]

[DOI]

CoRR, 2019

2018

Sampling Can Be Faster Than Optimization.

[BibT_eX]

[DOI]

CoRR, 2018

Stability and Convergence Trade-off of Iterative Optimization Algorithms.

[BibT_eX]

[DOI]

Yuansi Chen

Bin Yu

CoRR, 2018

Minimizing Nonconvex Population Risk from Rough Empirical Risk.

[BibT_eX]

[DOI]

CoRR, 2018

Stochastic Cubic Regularization for Fast Nonconvex Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

On the Local Minima of the Empirical Risk.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Is Q-Learning Provably Efficient?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Conference On Learning Theory, 2018

2017

Gradient Descent Can Take Exponential Time to Escape Saddle Points.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

How to Escape Saddle Points Efficiently.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis.

[BibT_eX]

[DOI]

Rong Ge

Yi Zheng

Proceedings of the 34th International Conference on Machine Learning, 2017

Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm.

[BibT_eX]

[DOI]

CoRR, 2016

Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences.

[BibT_eX]

[DOI]

Yuchen Zhang

Sivaraman Balakrishnan

Martin J. Wainwright

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Sham M. Kakade