Yu Bai
Yu Bai
Research Scientist, Salesforce Research
Verified email at salesforce.com - Homepage
Title
Cited by
Cited by
Year
The landscape of empirical risk for nonconvex losses
S Mei, Y Bai, A Montanari
The Annals of Statistics 46 (6A), 2747-2774, 2018
2092018
Proxquant: Quantized neural networks via proximal operators
Y Bai, YX Wang, E Liberty
International Conference on Learning Representations (ICLR) 2019, 2018
462018
Beyond linearization: On quadratic and higher-order approximation of wide neural networks
Y Bai, JD Lee
International Conference on Learning Representations (ICLR) 2020, 2019
432019
Approximability of discriminators implies diversity in GANs
Y Bai, T Ma, A Risteski
International Conference on Learning Representations (ICLR) 2019, 2018
432018
Provable self-play algorithms for competitive reinforcement learning
Y Bai, C Jin
International Conference on Machine Learning, 551-560, 2020
322020
Subgradient descent learns orthogonal dictionaries
Y Bai, Q Jiang, J Sun
International Conference on Learning Representations (ICLR) 2019, 2018
292018
Provably Efficient Q-Learning with Low Switching Cost
Y Bai, T Xie, N Jiang, YX Wang
Advances in Neural Information Processing Systems, 2019, 2019
232019
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning
M Yin, Y Bai, YX Wang
International Conference on Artificial Intelligence and Statistics, 1567-1575, 2021
182021
Near-Optimal Reinforcement Learning with Self-Play
Y Bai, C Jin, T Yu
arXiv preprint arXiv:2006.12007, 2020
182020
How Important is the Train-Validation Split in Meta-Learning?
Y Bai, M Chen, P Zhou, T Zhao, J Lee, S Kakade, H Wang, C Xiong
International Conference on Machine Learning, 543-553, 2021
92021
A sharp analysis of model-based reinforcement learning with self-play
Q Liu, T Yu, Y Bai, C Jin
International Conference on Machine Learning, 7001-7010, 2021
92021
Taylorized training: Towards better approximation of neural network training at finite width
Y Bai, B Krause, H Wang, C Xiong, R Socher
arXiv preprint arXiv:2002.04010, 2020
82020
Towards understanding hierarchical learning: Benefits of neural representations
M Chen, Y Bai, JD Lee, T Zhao, H Wang, C Xiong, R Socher
arXiv preprint arXiv:2006.13436, 2020
72020
Tapas: Two-pass approximate adaptive sampling for softmax
Y Bai, S Goldman, L Zhang
arXiv preprint arXiv:1707.03073, 2017
62017
Near-optimal offline reinforcement learning via double variance reduction
M Yin, Y Bai, YX Wang
arXiv preprint arXiv:2102.01748, 2021
52021
Exact gap between generalization error and uniform convergence in random feature models
Z Yang, Y Bai, S Mei
arXiv preprint arXiv:2103.04554, 2021
32021
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
Y Bai, S Mei, H Wang, C Xiong
arXiv preprint arXiv:2102.07856, 2021
22021
Proximal algorithms for constrained composite optimization, with applications to solving low-rank sdps
Y Bai, J Duchi, S Mei
arXiv preprint arXiv:1903.00184, 2019
22019
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
T Xie, N Jiang, H Wang, C Xiong, Y Bai
arXiv preprint arXiv:2106.04895, 2021
12021
Improved Uncertainty Post-Calibration via Rank Preserving Transforms
Y Bai, T Ma, H Wang, C Xiong
12020
The system can't perform the operation now. Try again later.
Articles 1–20