Jingfeng Wu

Jingfeng Wu / 吴京风

I am a Ph.D. candidate (2019 - now) at Johns Hopkins University, Computer Science Department. I am supervised by Prof. Vladimir Braverman. Previously I obtained B.S. (Mathematics, 2012 - 2016) and M.S. (Applied Math, 2016 - 2019) from Peking University, School of Mathematical Sciences.

Email / CV / Google Scholar / Github / Twitter

News

[May 2022] One paper is accepted to ICML 2022 as long presentation!
[Mar 2022] Will do an internship at Google Research Seattle during summer 2022.

[Jan 2022] One paper is accepted to AISTATS 2022.

[Dec 2021] Passed the PhD candidacy exam.

[Sep 2021] Two papers are accepted to NeurIPS 2021.

[Sep 2021] Talk on problem-dependent bound of constant-stepsize SGD at JHU CS Theory Seminar.

[May 2021] Awarded MINDS Summer Data Science Fellowship. Many thanks to the committee.

[May 2021] One paper is accepted to COLT 2021.

[Mar 2021] Talk on the implicit bias of SGD at UCLA.

[Feb 2021] In a relationship with Yuan, happy Valentine's day~

[Jan 2021] One paper is accepted to ICLR 2021.

[Nov 2020] Talk on the implicit bias of SGD at JHU CS Theory Seminar.

[Oct 2020] One paper will be presented at Workshop on Optimization for Machine Learning (OPT).

[May 2020] Two papers get accepted to ICML 2020.

[Mar 2020] Stay home stay safe.

[Nov 2019] One paper will be orally presented at Workshop on Optimization for Machine Learning (OPT).

[Sep 2019] Starting working at Hopkins. Veritas vos liberabit!

[Jun 2019] Graduated from Peking University.

[Apr 2019] One paper is accepted to ICML 2019.

[Mar 2019] One paper is accepted to CVPR 2019 as an oral presentation.

[Dec 2018] Looking for a Ph.D. position in machine learning / statistical learning starting from fall, 2019.

Research

My research focuses on providing theoretical understanding to machine learning problems stemmed from practice.

I am interested in understanding how algorithm "adapts" to problem in the statistical learning context, with a focus on studying algorithm-problem-dependent performance guarantees.
I am also interested in developing efficient machine learning algorithms, with an aim to connect theoretical guarantees with practical motivations.

Key Words: Machine Learning, Reinforcement Learning, Stochastic Gradient Descent, Sketching

Preprints

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
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.

Publications

	Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression 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.
	Gap-Dependent Unsupervised Exploration for Reinforcement Learning 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.
	The Benefits of Implicit Regularization from SGD in Least Squares Problems 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.
	Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning 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.
	Lifelong Learning with Sketched Structural Regularization 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.
	Benign Overfitting of Constant-Stepsize SGD for Linear Regression 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.
	Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate 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.
	Obtaining Adjustable Regularization for Free via Iterate Averaging 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.
	On the Noisy Gradient Descent that Generalizes as SGD 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.
	Tangent-Normal Adversarial Regularization for Semi-supervised Learning 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.
	The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects 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.

Services

Conference Reviewer: ICML 2020 - 2022; NeurIPS 2020 - 2022; ICLR 2021 - 2022; AISTATS 2021 - 2022
PC Member: AAAI 2021 - 2022
Journal Reviewer: TPAMI; JMLR

Awards

ICML 2021 Best Reviewers (Top 10%)
JHU MINDS 2021 Summer Data Science Fellowship

Experiences

Jun 2022 - Aug 2022: Research Intern at Google Research Seattle
Aug 2019 - Now: Research Assistant at Johns Hopkins University
Dec 2018 - May 2019: Research Intern at Baidu Big Data Lab
Jul 2017 - Dec 2018: Research Assistant at Peking University

Template: this