Learning via Wasserstein information geometry (基于Wasserstein信息几何的学习方法)

报告日期:2018-12-24 点击次数: 打印 字号:TT
  • 报告主题

    报告题目:Learning via Wasserstein information geometry

  • 摘要

    Recently optimal transport has many applications in machine learning. In this talk, we introduce dynamical optimal transport on machine learning models. We proposed to study these model as a Riemannian manifold with a Wasserstein metric. We call it Wasserstein information geometry. Various developments, especially the Fokker-Planck equation on learning models, will be introduced. The entropy production of Shannon entropy will be established. Many numerical examples, including restricted Boltzmann machine and generative adversary network, will be presented.

  • 教授简介

    Wuchen Li was born in Linyi, Shandong, China. He received his BSc in Mathematics from Shandong university in 2009, and a Ph.D. degree in Mathematics from Georgia institute of Technology in 2016. He is currently a computation and applied assistant professor in University of California, Los Angeles.

  • 报告时间及地点

    时间:2018年12月24日 星期一 上午10:00

  • 联系人

    向雪霜 xiangxueshuang@qxslab.cn