讲座题目：Wasserstein information geometric learning 主讲人：Wuchen Li Assistant professor 主持人：查宏远 教授 开始时间：2019-06-14 10:00:00 结束时间：2019-06-14 11:00:00 讲座地址：理科大楼A1514 主办单位：计算机科学与软件工程学院
报告人简介： Wuchen Li was from Shandong. 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. After then, he is appointed as a CAM assistant professor in University of California, Los Angeles. 报告内容： Optimal transport (Wasserstein metric) nowadays play important roles in data science and machine learning. In this talk, we brief review its development and applications in machine learning. In particular, we will focus its induced differential structure. We will introduce the Wasserstein natural gradient in parametric models. The metric tensor in probability density space is pulled back to the one on parameter space. We derive the Wasserstein gradient flows and proximal operator in parameter space. We demonstrate that the Wasserstein natural gradient works efficiently in several statistical machine learning problems, including Boltzmann machine, generative adversary models (GANs) and variational Bayesian statistics. |
