Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Yu Bai

Understanding the Under-Coverage Bias in Uncertainty Estimation


Jun 10, 2021
Yu Bai, Song Mei, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

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


Jun 09, 2021
Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai


  Access Paper or Ask Questions

Cross-Lingual Abstractive Summarization with Limited Parallel Resources


May 31, 2021
Yu Bai, Yang Gao, Heyan Huang

* Accepted by ACL2021 

  Access Paper or Ask Questions

Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network


Mar 30, 2021
Bo Dong, Hao Liu, Yu Bai, Jinbiao Lin, Zhuoran Xu, Xinyu Xu, Qi Kong

* NIPS2020 Workshop on Machine Learning for Autonomous Driving 

  Access Paper or Ask Questions

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


Mar 08, 2021
Zitong Yang, Yu Bai, Song Mei


  Access Paper or Ask Questions

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


Feb 23, 2021
Yu Bai, Chi Jin, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Localized Calibration: Metrics and Recalibration


Feb 22, 2021
Rachel Luo, Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai, Shengjia Zhao, Stefano Ermon


  Access Paper or Ask Questions

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


Feb 15, 2021
Yu Bai, Song Mei, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction


Feb 02, 2021
Ming Yin, Yu Bai, Yu-Xiang Wang


  Access Paper or Ask Questions

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


Oct 12, 2020
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

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


Oct 04, 2020
Qinghua Liu, Tiancheng Yu, Yu Bai, Chi Jin


  Access Paper or Ask Questions

Near-Optimal Reinforcement Learning with Self-Play


Jul 14, 2020
Yu Bai, Chi Jin, Tiancheng Yu


  Access Paper or Ask Questions

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


Jul 07, 2020
Ming Yin, Yu Bai, Yu-Xiang Wang

* Appendix included 

  Access Paper or Ask Questions

Towards Understanding Hierarchical Learning: Benefits of Neural Representations


Jun 24, 2020
Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

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


Feb 24, 2020
Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Provable Self-Play Algorithms for Competitive Reinforcement Learning


Feb 23, 2020
Yu Bai, Chi Jin


  Access Paper or Ask Questions

Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning


Oct 21, 2019
Ke Zhan, Shimiao Jiang, Yu Bai, Yi Li, Xu Liu, Zhuoran Xu

* Proceedings of the British Machine Vision Conference (BMVC), 2019 

  Access Paper or Ask Questions

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


Oct 03, 2019
Yu Bai, Jason D. Lee


  Access Paper or Ask Questions

Provably Efficient Q-Learning with Low Switching Cost


May 30, 2019
Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang


  Access Paper or Ask Questions

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


Mar 01, 2019
Yu Bai, John Duchi, Song Mei


  Access Paper or Ask Questions

Subgradient Descent Learns Orthogonal Dictionaries


Oct 25, 2018
Yu Bai, Qijia Jiang, Ju Sun


  Access Paper or Ask Questions

ProxQuant: Quantized Neural Networks via Proximal Operators


Oct 08, 2018
Yu Bai, Yu-Xiang Wang, Edo Liberty


  Access Paper or Ask Questions

Approximability of Discriminators Implies Diversity in GANs


Jul 24, 2018
Yu Bai, Tengyu Ma, Andrej Risteski


  Access Paper or Ask Questions

CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices


Aug 29, 2017
Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yipeng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan

* 14 pages, 15 Figures, conference 

  Access Paper or Ask Questions

TAPAS: Two-pass Approximate Adaptive Sampling for Softmax


Jul 14, 2017
Yu Bai, Sally Goldman, Li Zhang


  Access Paper or Ask Questions

The Landscape of Empirical Risk for Non-convex Losses


Jan 14, 2017
Song Mei, Yu Bai, Andrea Montanari

* This version presents a general framework, and applies it to several statistical learning problems 

  Access Paper or Ask Questions