Talk by Gabriel Peyre (CNRS and Ecole Normale Superieure)

01/25/2021 WebEx Meeting  9:15-10:00 am

 

Abstract: Optimal transport (OT) has recently gained lot of interest in machine learning. It is a natural tool to compare in a geometrically faithful way probability distributions. It finds applications in both supervised learning (using geometric loss functions) and unsupervised learning (to perform generative model fitting). OT is however plagued by the curse of dimensionality, since it might require a number of samples which grows exponentially with the dimension. In this talk, I will explain how to leverage entropic regularization methods to define computationally efficient loss functions, approximating OT with a better sample complexity. More information and references can be found on the website of our book "Computational Optimal Transport" https://optimaltransport.github.io/

Bio: Gabriel Peyré is senior researcher at the Centre Nationale de Recherche Scientifique (CNRS) and professor at the Ecole Normale Supérieure, Paris. His research is focused on using Optimal Transport methods for machine learning. He is the creator of the "Numerical tour of data sciences" (www.numerical-tours.com), a popular online repository of Python/Matlab/Julia/R resources to teach mathematical data sciences. His research is supported by a European ERC consolidator grant. He is the recipient of the Blaise-Pascal prize from the French Academy of sciences in 2017 and the Enrico Magenes Prize from the Italian Mathematical Union in 2019.