We announce the following DEC Statistics seminar:
Thursday, November 28 12:30 Meeting room 3-e4-sr03, Bocconi University, Via Roentgen 1, 3rd floor
Quentin Berthet (Google Research)
Title: Optimal transport methods in statistics and machine learning: theory and applications
Abstract: Optimal transport is one of the foundational problems of optimization, and a very important topic in analysis. It asks how one can transport mass with a given measure to have another measure, with minimal global transport cost. The associated Wasserstein distance is a useful statistical tool to compare distributions, taking into account geometric properties of the data. In this presentation, I will talk about two recent projects on this topic. In the first one, we propose a novel approach for unsupervised embedding alignment, and show applications to natural language processing. It is based on a new approach for Wasserstein loss minimization (joint work with E. Grave and A. Joulin). In the second one, we provide new methods and guarantees for estimation of distributions with smooth densities, in the Wasserstein distance. We show that these tools, inspired by techniques in nonparametric statistics, yield information-theoretic optimal results. We also develop ideas to handle our proposed estimators in a computationally efficient manner, and explore some of the associated computational trade-offs (joint work with J. Weed).
Kind regards, Giacomo Zanella
The DEC statistics seminars schedule is available at http://www.unibocconi.eu/statseminar
Please note: if you are a guest and you do not have a Bocconi ID Card to access to the Bocconi Buildings, please communicate your participation by sending an email to elisa.picassi@unibocconi.it