Princeton University

School of Engineering & Applied Science

Large-scale optimal transport: statistics and computation

Jonathan Weed, Massachusetts Institute of Technology
B205 Engineering Quadrangle
Thursday, January 17, 2019 - 4:30pm


Optimal transport is a concept from probability which has recently seen an explosion of interest in machine learning and statistics as a tool for analyzing high-dimensional data. However, the key obstacle in using optimal transport in practice has been its high statistical and computational cost. In this talk, we show how different notions of regularization can lead to better statistical rates—beating the curse of dimensionality—and state-of-the-art algorithms.


Jonathan Weed is a fifth-year PhD student in Mathematics and Statistics at Massachusetts Institute of Technology. Prior to MIT, he received his AB in Mathematics from Princeton University. He researches theoretical aspects of machine learning, with a particular focus on the statistical analysis of data with geometric structure. He is a recipient of an NSF Graduate Student Fellowship, an MIT Presidential Fellowship, and the Josephine de Kármán fellowship.