\dm_csml_event_details UCL ELLIS

A primer on PAC-Bayesian learning with applications to deep neural networks


Speaker

Benjamin Guedj

Affiliation

UCL - INRIA

Date

Friday, 28 June 2019

Time

13:00-14:00

Location

Zoom

Link

Gatsby Computational Neuroscience Unit Ground Floor

Event series

DeepMind/ELLIS CSML Seminar Series

Abstract

PAC-Bayes is a generic and flexible framework to address generalisation abilities of machine learning algorithms. It leverages the power of Bayesian inference and allows to derive new learning strategies. Benjamin will briefly present the key concepts of PAC-Bayes and illustrate how it can be used to study generalization properties of deep neural networks.

Joint work with Gaël Letarte, Pascal Germain, François Laviolette (https://arxiv.org/abs/1905.13367) and John Shawe-Taylor (see our ICML 2019 tutorial https://bguedj.github.io/icml2019/index.html)

Slides from the talk here

Biography