Bayes in Grenoble: Julyan Arbel

on the September 19, 2019

September 19, at 2:00 pm
Julyan Arbel from Inria Grenoble Rhône-Alpes will talk about "Some theory on Bayesian neural networks". The event will take place on September, 19 at 2:00 pm at IMAG building.
Bayes in Grenoble is a new reading group on Bayesian statistical methods. The purpose of this group is to gather the Grenoble Bayesian community on a monthly basis around noteworthy papers. Those can equally focus on theory, methods, learning, applications, computations, etc, and can be seminal papers as well as recent preprints, as soon as they relate to Bayes.

The reading group is organised by Julyan Arbel and Florence Forbes. Feel free to contact them if you wish to attend/be added to the mailing list and/or give a talk. https://sites.google.com/view/bigseminar/accueil

React on social media: #BIGseminar

19 September 2019, Julyan Arbel (Inria Grenoble Rhône-Alpes)

Some theory on Bayesian neural networks
Abstract

In this talk, we first present seminal works at the basis of the theory of Bayesian neural networks. These include Radford Neal result in the 90s regarding the connexion between Gaussian processes and wide neural networks, and the recent developments of this result to deep neural networks. In a second part, we focus on understanding priors in Bayesian neural networks at the unit level. More specifically, we investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. We establish that the induced prior distribution on the units before and after activation becomes increasingly heavy-tailed with the depth of the layer.

Joint work with Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo.

Link: http://proceedings.mlr.press/v97/vladimirova19a/vladimirova19a.pdf




 
Published on February 25, 2020

Practical informations

Lieu(x)


Room 406
IMAG building