Resumo: Optimal Transport (OT) is a rich field in mathematics that intersects optimization, statistics, analysis, and applied mathematics. In this talk, I will begin by introducing the fundamental definitions and theoretical concepts of OT, followed by a brief overview of its central problems. The second part of the presentation will focus on three applications: two in statistics and one in machine learning. The first statistical application involves an inference problem framed by the continuity equation, while the second concerns estimating the projection of a Gaussian distribution using empirical entropic projections. Finally, I will discuss how machine learning models respond to shifts in the distribution of input variables, proposing an explainability framework based on Wasserstein distance.

Texto informado pelo autor.

* Os participantes dos seminários não poderão acessar às dependências da FGV usando bermuda, chinelos, blusa modelo top ou cropped, minissaia ou camiseta regata. O uso da máscara é facultativo, porém é obrigatória a apresentação do comprovante de vacinação (físico ou digital).