|
|||||||||||||||||||||||||
|
See More |
My research focuses on providing theoretical understanding to machine learning problems stemmed from practice.
|
![]() |
Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu, Sham M. Kakade arXiv, 2022 bibtex / arXiv We consider the risk bounds for multi-pass SGD (with replacement) in the interpolating regime, and compare it with batch GD. |
![]() |
Jingfeng Wu*, Difan Zou*, Vladimir Braverman, Quanquan Gu, Sham M. Kakade International Conference on Machine Learning (ICML), 2022, long presentation bibtex / arXiv We prove problem-dependent excess risk bounds for the last iterate of SGD in overparameterized linear regression problems. |
![]() |
Jingfeng Wu, Vladimir Braverman, Lin F. Yang International Conference on Artificial Intelligence and Statistics (AISTATS), 2022 bibtex / arXiv / slides / poster / code We show an improved sample complexity for unsupervised reinforcement learning when the problem instances have constant sub-optimality gap. |
![]() |
Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu, Dean P. Foster, Sham M. Kakade Conference on Neural Information Processing Systems (NeurIPS), 2021 bibtex / arXiv We show that in a broad class of interesting least square instances, SGD is always nearly as good as ridge regression, but ridge regression could be much worse than SGD. |
![]() |
Jingfeng Wu, Vladimir Braverman, Lin F. Yang Conference on Neural Information Processing Systems (NeurIPS), 2021 bibtex / arXiv / slides / poster / code We study the regret bound and sample complexity for multi-objective reinforcement learning with potentially adversarial preferences. |
![]() |
Haoran Li, Aditya Krishnan, Jingfeng Wu, Soheil Kolouri, Praveen K. Pilly, Vladimir Braverman Asian Conference on Machine Learning (ACML), 2021 bibtex / arXiv We show sketching methods improve structural regularization algorithms for lifelong learning. |
![]() |
Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu, Sham M. Kakade Annual Conference on Learning Theory (COLT), 2021 bibtex / arXiv / slides We study the generalization bounds of SGD for overparameterized linear regression problems. |
![]() |
Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu International Conference on Learning Representations (ICLR), 2021 bibtex / arXiv / slides / poster We show a directional bias for SGD with moderate learning rate. This particular effect cannot be achieved by GD or SGD with small learning rate. |
![]() |
Jingfeng Wu, Vladimir Braverman, Lin F. Yang International Conference on Machine Learning (ICML), 2020 bibtex / arXiv / slides / code We show that an l2-type regularization effect could be achieved via properly averaging an optimization path in many cases. |
![]() |
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Vladimir Braverman, Zhanxing Zhu International Conference on Machine Learning (ICML), 2020 bibtex / arXiv / slides / code For gradient methods with noises, we show that the distribution classes of the noises do not affect their regularization effects. |
![]() |
Bing Yu*, Jingfeng Wu*, Jinwen Ma, Zhanxing Zhu Conference on Computer Vision and Pattern Recognition (CVPR), 2019, oral bibtex / arXiv / slides / poster / code We present a novel manifold regularization method for semi-supervised learning. The regularizer is realized via adversarial training. |
![]() |
Zhanxing Zhu*, Jingfeng Wu*, Bing Yu, Lei Wu, Jinwen Ma International Conference on Machine Learning (ICML), 2019 bibtex / arXiv / slides / poster / code We study the noise structure of stochastic gradient descent, and demonstrate its benefits on helping the dynamic escape from sharp minima. |
|
|
|
Template: this |