BIDSA Webinar: “Differentiating Through Optimal Transport”

Marco Cuturi (Google Brain / ENSAE)    

March 18, 2021 | 5pm CET | Zoom

Computing or approximating an optimal transport cost is rarely the sole goal when using OT in applications. 

In most cases the end goal relies instead on solving the OT problem and studying the differentiable properties of its solutions w.r.t. to arbitrary input. 

I will present in this talk recent applications that highlight this necessity, as well as concrete algorithmic and programmatic solutions to handle such issues.

Marco Cuturi joined Google Brain, in Paris, in October 2018. He graduated from ENSAE (2001), ENS Cachan (Master MVA, 2002) and holds a PhD in applied maths obtained in 2005 at Ecole des Mines de Paris. He worked as a post-doctoral researcher at the Institute of Statistical Mathematics, Tokyo, between 11/2005 and 3/2007. He worked in the financial industry between 4/2007 and 9/2008. After working at the ORFE department of Princeton University between 02/2009 and 08/2010 as a lecturer, he was at the Graduate School of Informatics of Kyoto University between 9/2010 and 9/2016 as a tenured associate professor from 10/2013. He then joined ENSAE, the french national school for statistics and economics, in 9/2016, where he still teaches. His recent proposal to solve optimal transport using an entropic regularization has re-ignited interest in optimal transport and Wasserstein distances in the machine learning community. His work has recently focused on applying that loss function to problems involving probability distributions, e.g. topic models / dictionary learning for text and images, parametric inference for generative models, regression with a Wasserstein loss and probabilistic embeddings for words.