学术报告

A Fast Proximal Point Method for Computing Exact Wasserstein Distance

阅读次数:860

题目:A Fast Proximal Point Method for Computing Exact Wasserstein Distance
报告人:王祥丰 副教授 (华东师范大学 计算机科学与软件工程澳门新葡萄京888)
地点:致远楼103室
时间:2019年5月21日下午2:00-3:00
报告摘要:
Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when applies to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.

欢迎各位参加!

联系我们

    电话:86-21-65981384

    地址:上海市四平路1239号 致远楼

快速通道

Copyright © 2018  澳门新葡萄京888官网-注册娱乐所有网站 版权所有.

XML 地图 | Sitemap 地图