El Instituto de Ingeniería Matemática y Computacional (IMC) los saluda atentamente y los invita al seminario que se dictará la próxima semana.
La charla se efectuará el miércoles 13 de abril a las 13 horas, a través de la plataforma Zoom, cuyo enlace se puede obtener escribiendo a Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.. La información sobre la charla la pueden encontrar en el poster adjunto y abajo.
Título: Schrödinger Bridges and Sinkhorn algorithm through the lens of Optimal Transport Theory
Expositor: Augusto Gerolin
Afiliación: Department of Mathematics and Statistics and Department of Chemistry and Biomolecular Sciences, University of Ottawa
Fecha: Miércoles 13 de abril de 2022, 1:00 PM
Lugar: Zoom
Abstract:
In this talk we will give a friendly introduction to the Sinkhorn algorithm (aka Matrix Scaling, Iterative Proportional Fitting Procedure, etc) in the context of optimal transportation theory. We will exploit the equivalence between the Schrödinger Bridge problem and the Shannon entropy penalized optimal transport in order to find a different approach to the duality, in the spirit of optimal transport. In particular, this duality approach extends to more general convex entropy penalizations, provides an alternative proof of the convergence of the Sinkhorn algorithm with two marginals and shows convergence of the Sinkhorn algorithm in the multi-marginal case.
The talk has few prerequisites and no contraindications. Therefore, MSc and PhD students are encouraged to attend as well.
Bio:
Augusto Gerolin is a Canada Research Chair in Artificial Intelligence at the Interface of Chemistry and Mathematics and is an Assistant Professor jointly appointed to the uOttawa Departments of Mathematics and Statistics and of Chemistry and Biomolecular Sciences. Previously, he was a Marie Skłodowska-Curie fellow at the Theoretical Chemistry section of the Vrije Universiteit Amsterdam (Netherlands). He obtained his PhD degree at the University of Pisa (Italy). Gerolin's research interests include Optimal Transport Theory, Mathematical Physics, Theoretical and Computational Chemistry and Mathematical aspects of Machine Learning Theory.
