Dimension Reduction Techniques in Optimal Transport Problems
报告人：孟澄教授（中国人民大学）
时间：2021-05-20 14:00-16:00
地点：理科1号楼，1114
Abstract:
Recently, optimal transport methods have drawn great attention in statistics, machine learning, and computer science due to their close relationship to deep generative neural networks. Despite its broad applications, the estimation of high-dimensional Wasserstein distances is a well-known challenging problem owing to the curse of dimensionality. In this talk, we will introduce some cutting-edge dimension reduction techniques that tackle high-dimensional optimal transport problems. We will also cover some recent studies, which indicate OT methods themselves, surprisingly, can be utilized to construct dimension reduction tools. Open challenges will be discussed at the end of the talk.
About the Speaker:
孟澄，中国人民大学统计与大数据研究院助理教授、博士生导师。2015年毕业于清华大学数学系，2020年毕业于美国佐治亚大学统计系，师从马平教授与钟文瑄教授，获统计学博士学位。主要研究方向包括：大数据里的抽样和降维问题，最优传输中的计算问题和理论分析，光滑样条，医学影像数据和三维点云数据处理与分析，以及传统统计和深度学习之间的联系等。
