Skip to main content
Home

Main navigation

  • Home
  • Series
  • People
  • Depts & Colleges
  • Open Education

Main navigation

  • Home
  • Series
  • People
  • Depts & Colleges
  • Open Education

A primer on PAC-Bayesian learning *followed by* News from the PAC-Bayes frontline

Series
Department of Statistics
Video Audio Embed
Benjamin Guedj, University College London, gives a OxCSML Seminar on 26th March 2021.
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. I will briefly present the key concepts of PAC-Bayes and highlight a few recent contributions from my group.

More in this series

View Series
Department of Statistics

Approximate Bayesian computation with surrogate posteriors

Julyan Arbel (Inria Grenoble - Rhône-Alpes), gives an OxCSML Seminar on Friday 30th April 2021, for the Department of Statistics.
Previous
Department of Statistics

Several structured thresholding bandit problems

OxCSML Seminar - Friday 28th May 2021, presented by Alexandra Carpentier (University of Magdeburg).
Next
Transcript Available

Episode Information

Series
Department of Statistics
People
Benjamin Guedj
Keywords
statistics
Bayesian
mathematics
machine learning
ai
Department: Department of Statistics
Date Added: 28/05/2021
Duration: 00:59:06

Subscribe

Apple Podcast Video Apple Podcast Audio Audio RSS Feed Video RSS Feed

Download

Download Video Download Audio Download Transcript

Footer

  • About
  • Accessibility
  • Contribute
  • Copyright
  • Contact
  • Privacy
'Oxford Podcasts' Twitter Account @oxfordpodcasts | MediaPub Publishing Portal for Oxford Podcast Contributors | Upcoming Talks in Oxford | © 2011-2022 The University of Oxford