Jingfeng Wu

I am a first year Ph.D. student at Johns Hopkins University, Computer Science Department. I work with Prof. Vladimir Braverman.

Previously, I obtained my B.S. and M.S. at Peking University, School of Mathematical Sciences. During my Masters period, I was luckily to be supervised by Prof. Jinwen Ma and Prof. Zhanxing Zhu.

Email  /  CV  /  Google Scholar  /  Github

  • One paper is accepted to ICML-2019: "The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects".
  • Our paper "Tangent-Normal Adversarial Regularization for Semi-supervised Learning" is accepted as an oral presentation to CVPR-2019!

I'm interested in both the theoretical and applied parts of machine learning. Currently, I am following cutting edge researches in: 1) theoretically machine learning, 2) stochastic algorithms, 3) generative models, 4) adversarial learning, 5) explainable computer vision.


The Multiplicative Noise in Stochastic Gradient Descent: Data-Dependent Regularization, Continuous and Discrete Approximation
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Zhanxing Zhu
bibtex / arXiv

We re-interpret the noise in SGD from the perspective of random sampling, and obtain several novel results in regard to understand the regularization and approximation of SGD.


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

We present a novel manifold regularization method for semi-supervised learning, which 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

We study the noise structure of stochastic gradient descent, and demonstrate its benefits on helping the dynamic escaping from sharp minima.


Template: this