Yu Bai

About me: I am a Senior Research Scientist at Salesforce AI Research in Palo Alto, CA. Before joining Salesforce, I completed my PhD in Statistics at Stanford University (specializing in machine learning) in September 2019, where I was fortunate to be advised by Prof. John Duchi and was a member of the Machine Learning Group. During my PhD I also spent times at the research labs of Google and Amazon. Prior to Stanford, I was an undergrad in mathematics at Peking University. My research interest lies broadly in machine learning, with recent focus on Theoretical foundations of deep learning (blog post); Reinforcement learning theory (slides on partially observable RL); Multi-agent reinforcement learning and games (blog post, slides on MARL, slides on Extensive-Form Games); Uncertainty quantification (slides). News: [Mar 2023] I will serve as an Area Chair for NeurIPS 2023. [Jan 2023] Three papers accepted at ICLR 2023. [Nov 2022] Excited to be giving an invited talk “Recent Progresses on the Theory of Multi-Agent Reinforcement Learning and Games” at Stanford CS332. [Sep 2022] Four papers accepted at NeurIPS 2022. [May 2022] Excited to be speaking at the RL theory seminar about our work on sample-efficient learning of general-sum Markov Games with a large number of players! [May 2022] Our paper on near-optimal learning in extensive-form games is accepted at ICML 2022. We achieve this by two new algorithms (Balanced OMD, Balanced CFR). [Jan 2022] Two papers accepted at ICLR 2022, on sample-efficient RL in multi-agent general-sum Markov games, and improved conformal prediction with general families of prediction sets. Contact: yu.bai (at) salesforce.com Curriculum Vitae | Google Scholar Profile | Github Follow @yubai01

Research

Preprints

• Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation.
  Yuanhao Wang, Qinghua Liu, Yu Bai, Chi Jin.
  

• Lower Bounds for Learning in Revealing POMDPs.
  Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai.
  

• Improved Online Conformal Prediction via Strongly Adaptive Online Learning.
  Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Yu Bai.
  

• Offline Learning in Markov Games with General Function Approximation.
  Yuheng Zhang, Yu Bai, Nan Jiang.
  

• Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning.
  Fan Chen, Song Mei, Yu Bai.
  

Publications

• Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms.
  Fan Chen, Yu Bai, Song Mei.
  ICLR 2023 (Notable-top-25% / “Spotlight”).

• The Role of Coverage in Online Reinforcement Learning.
  Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade.
  ICLR 2023 (Notable-top-5% / “Oral”).

• Learning Rationalizable Equilibria in Multiplayer Games.
  Yuanhao Wang, Dingwen Kong, Yu Bai, Chi Jin.
  ICLR 2023.

• Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent.
  Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu.
  NeurIPS 2022 (Oral).

• Policy Optimization for Markov Games: Unified Framework and Faster Convergence.
  Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai.
  NeurIPS 2022.

• Identifying Good Directions to Escape the NTK Regime and Efficiently Learn Low-Degree Plus Sparse Polynomials.
  Eshaan Nichani, Yu Bai, Jason D. Lee.
  NeurIPS 2022.

• Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games.
  Ziang Song, Song Mei, Yu Bai.
  NeurIPS 2022.

• Conformal Predictor for Improving Zero-Shot Text Classification Efficiency.
  Prafulla Kumar Choubey, Yu Bai, Chien-Sheng Wu, Wenhao Liu, Nazneen Rajani.
  EMNLP 2022.

• Local Calibration: Metrics and Recalibration.
  Rachel Luo, Aadyot Bhatnagar, Yu Bai, Shengjia Zhao, Huan Wang, Caiming Xiong, Silvio Savarese, Edward Schmerling, Marco Pavone.
  UAI 2022.

• Near-Optimal Learning of Extensive-Form Games with Imperfect Information.
  Yu Bai, Chi Jin, Song Mei, Tiancheng Yu.
  ICML 2022.

• When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?
  Ziang Song, Song Mei, Yu Bai.
  ICLR 2022.

• Efficient and Differentiable Conformal Prediction with General Function Classes.
  Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong.
  ICLR 2022. [Code]

• Understanding the Under-Coverage Bias in Uncertainty Estimation.
  Yu Bai, Song Mei, Huan Wang, Caiming Xiong.
  NeurIPS 2021 (Spotlight).
  

• Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning.
  Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai.
  NeurIPS 2021.
  

• Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games.
  Yu Bai, Chi Jin, Huan Wang, Caiming Xiong.
  NeurIPS 2021.
  

• Near-Optimal Offline Reinforcement Learning via Double Variance Reduction.
  Ming Yin, Yu Bai, Yu-Xiang Wang.
  NeurIPS 2021.
  

• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification.
  Yu Bai, Song Mei, Huan Wang, Caiming Xiong.
  ICML 2021.

• Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models.
  Zitong Yang, Yu Bai, Song Mei.
  ICML 2021.

• How Important is the Train-Validation Split in Meta-Learning?
  Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong.
  ICML 2021.

• A Sharp Analysis of Model-based Reinforcement Learning with Self-Play.
  Qinghua Liu, Tiancheng Yu, Yu Bai, Chi Jin.
  ICML 2021.

• Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning.
  Ming Yin, Yu Bai, Yu-Xiang Wang.
  AISTATS 2021 (Oral).
  

• Towards Understanding Hierarchical Learning: Benefits of Neural Representations.
  Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher.
  NeurIPS 2020.
  

• Near-Optimal Reinforcement Learning with Self-Play.
  Yu Bai, Chi Jin, Tiancheng Yu.
  NeurIPS 2020.
  

• Provable Self-Play Algorithms for Competitive Reinforcement Learning.
  Yu Bai, Chi Jin.
  ICML 2020.

• Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks.
  Yu Bai, Jason D. Lee.
  ICLR 2020.

• Provably Efficient Q-Learning with Low Switching Cost.
  Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang.
  NeurIPS 2019.

• Subgradient Descent Learns Orthogonal Dictionaries.
  Yu Bai, Qijia Jiang, Ju Sun.
  ICLR 2019.

• ProxQuant: Quantized Neural Networks via Proximal Operators.
  Yu Bai, Yu-Xiang Wang, Edo Liberty.
  ICLR 2019. [Code]

• Approximability of Discriminators Implies Diversity in GANs.
  Yu Bai, Tengyu Ma, Andrej Risteski.
  ICLR 2019.

• The Landscape of Empirical Risk for Nonconvex Losses.
  Song Mei, Yu Bai, Andrea Montanari, 2016.
  The Annals of Statistics, Volume 46, Number 6A (2018), 2747-2774.

Other technical reports

• Finding General Equilibria in Many-Agent Economic Simulations Using Deep Reinforcement Learning.
  Michael Curry, Alexander Trott, Soham Phade, Yu Bai, Stephan Zheng.
  

• Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width.
  Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher.
  [Code]

• Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs.
  Yu Bai, John C. Duchi, Song Mei.
  

• Analysis of Sequantial Quadratic Programming through the Lens of Riemannian Optimization.
  Yu Bai, Song Mei.
  

• TAPAS: Two-pass Approximate Adaptive Sampling for Softmax.
  Yu Bai, Sally Goldman, Li Zhang.
  

Talks

• When Can We Learn General-Sum Markov Games Sample-Efficiently with A Large Number of Players?
  RL Theory Virtual Seminars, May 2022.

• Near-Optimal Learning of Extensive-Form Games with Imperfect Information.
  Learning and Games Program, Simons Institute, April 2022.
  CISS Conference, Princeton University, March 2022.

• Understanding the Under-Coverage Bias in Uncertainty Estimation.
  Statistics Department Seminar, Rutgers University, October 2021.
  Spotlight presentation at ICML 2021 Workshop on Distribution-free Uncertainty Quantification, July 2021.

• Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games.
  Spotlight presentation at ICML 2021 Workshop on Reinforcement Learning Theory, July 2021.

• How Important is the Train-Validtaion Split in Meta-Learning?
  One World Seminar on the Mathematics of Machine Learning, October 2020.

• Provable Self-Play Algorithms for Competitive Reinforcement Learning.
  ICML, July 2020.
  Facebook AI Research, March 2020.

• Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks.
  Simons Institute, August 2020.
  ICLR, April 2020.

• Subgradient Descent Learns Orthogonal Dictionaries.
  ICLR, May 2019, New Orleans, LA.
  

• ProxQuant: Quantized Neural Networks via Proximal Operators
  ICLR, May 2019, New Orleans, LA.
  Bytedance AI Lab, Dec 2018, Menlo Park, CA.
  Amazon AI, Sep 2018, East Palo Alto, CA.

• On the Generalization and Approximation in Generative Adversarial Networks (GANs)
  ICLR, May 2019, New Orleans, LA.
  Google Brain, Nov 2018, Mountain View, CA.
  Salesforce Research, Nov 2018, Palo Alto, CA.
  Stanford ML Seminar, Oct 2018, Stanford, CA.

• Optimization Landscape of some Non-convex Learning Problems
  Stanford Theory Seminar, Apr 2018, Stanford, CA.
  Stanford ML Seminar, Apr 2017, Stanford, CA.

Service

• Area chair / Senior program committee: NeurIPS (2023), AIStats (2023).
  

• Conference reviewing: NeurIPS (2018-2022), ICLR (2019-2023), ICML (2019-2021, 2023), COLT (2019-2020, 2022-2023), FOCS (2022), AIStats (2020), IEEE-ISIT (2018).
  

• Journal reviewing: TMLR (Transactions of Machine Learning Research), The Annals of Statistics, JASA (Journal of the American Statistical Association), JRSS-B (Journal of the Royal Statistical Society: Series B), JMLR (Journal of Machine Learning Research), IEEE-TSP (Transactions on Signal Processing), SICON (SIAM Journal on Control and Optimization).