Seminar series
Date
Wed, 29 Jun 2022
Time
16:00 - 17:00
Speaker
Francis Bach
Organisation
INRIA - Ecole Normale Supérieure

The join button will be published 30 minutes before the seminar starts (login required).

I will consider the analysis of probability distributions through their associated covariance operators from reproducing kernel Hilbert spaces. In this talk, I will show that the von Neumann entropy and relative entropy of these operators are intimately related to the usual notions of Shannon entropy and relative entropy, and share many of their properties. They come together with efficient estimation algorithms from various oracles on the probability distributions. I will also present how these new notions of relative entropy lead to new upper-bounds on log partition functions, that can be used together with convex optimization within variational inference methods, providing a new family of probabilistic inference methods (based on https://arxiv.org/pdf/2202.08545.pdf, see also https://francisbach.com/information-theory-with-kernel-methods/).

Further Information

Please contact us for feedback and comments about this page.  Last update on 05 Apr 2022 - 14:21.