PAC-Bayes Unleashed: Generalisation Bounds with Unbounded Losses

PAC-Bayes Unleashed: Generalisation Bounds with Unbounded Losses

We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions. This extends the relevance and applicability of the PAC-Bayes learning framework, where most of the existing literature focuses on supervised learning problems with a bounded loss function (typical...

Full description

Bibliographic Details
Main Authors: Maxime Haddouche, Benjamin Guedj, Omar Rivasplata, John Shawe-Taylor
Format: Article
Language:English
Published: MDPI AG 2021-10-01
Series:Entropy
Subjects:
statistical learning theory
PAC-Bayes
generalisation bounds
Online Access:https://www.mdpi.com/1099-4300/23/10/1330

Internet

https://www.mdpi.com/1099-4300/23/10/1330

Similar Items