Jingfeng Wu

I am a third year master student at Peking University, School of Mathematical Science. Previously, I obtained my B.S. from Peking University, School of Mathematics and Science. I am supervised by Prof. Jinwen Ma and Dr. Zhanxing Zhu.

Email  /  CV  /  Google Scholar  /  Github

News
  • I am looking for a PhD position in machine learning / statistic learning starting from fall, 2019. If you are interested in working with me, please do not hesitate to contact me.
  • Our paper "Tangent-Normal Adversarial Regularization for Semi-supervised Learning" is accepted as an oral presentation by CVPR-2019!
Research

I'm interested in both the theoretical and applied parts of machine learning. Specifically, I am following cutting edge researches in: 1) theoretically machine learning analysis, 2) generative models and latent variable models, 3) adversarial learning, 4) semi-supervised learning, 5) applications in computer vision.

b3do

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

We present a novel manifold regularization method for semi-supervised learning, which is realized via adversarial training.

b3do

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
arXiv Preprint, 2018
arXiv

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

Experience
Blogs

Template: this