Saved in:
Bibliographic Details
Main Authors: Picard-Weibel, Antoine, Moscoviz, Roman, Guedj, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.10230
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915035168636928
author Picard-Weibel, Antoine
Moscoviz, Roman
Guedj, Benjamin
author_facet Picard-Weibel, Antoine
Moscoviz, Roman
Guedj, Benjamin
contents PAC-Bayes learning is a comprehensive setting for (i) studying the generalisation ability of learning algorithms and (ii) deriving new learning algorithms by optimising a generalisation bound. However, optimising generalisation bounds might not always be viable for tractable or computational reasons, or both. For example, iteratively querying the empirical risk might prove computationally expensive. In response, we introduce a novel principled strategy for building an iterative learning algorithm via the optimisation of a sequence of surrogate training objectives, inherited from PAC-Bayes generalisation bounds. The key argument is to replace the empirical risk (seen as a function of hypotheses) in the generalisation bound by its projection onto a constructible low dimensional functional space: these projections can be queried much more efficiently than the initial risk. On top of providing that generic recipe for learning via surrogate PAC-Bayes bounds, we (i) contribute theoretical results establishing that iteratively optimising our surrogates implies the optimisation of the original generalisation bounds, (ii) instantiate this strategy to the framework of meta-learning, introducing a meta-objective offering a closed form expression for meta-gradient, (iii) illustrate our approach with numerical experiments inspired by an industrial biochemical problem.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10230
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning via Surrogate PAC-Bayes
Picard-Weibel, Antoine
Moscoviz, Roman
Guedj, Benjamin
Machine Learning
PAC-Bayes learning is a comprehensive setting for (i) studying the generalisation ability of learning algorithms and (ii) deriving new learning algorithms by optimising a generalisation bound. However, optimising generalisation bounds might not always be viable for tractable or computational reasons, or both. For example, iteratively querying the empirical risk might prove computationally expensive. In response, we introduce a novel principled strategy for building an iterative learning algorithm via the optimisation of a sequence of surrogate training objectives, inherited from PAC-Bayes generalisation bounds. The key argument is to replace the empirical risk (seen as a function of hypotheses) in the generalisation bound by its projection onto a constructible low dimensional functional space: these projections can be queried much more efficiently than the initial risk. On top of providing that generic recipe for learning via surrogate PAC-Bayes bounds, we (i) contribute theoretical results establishing that iteratively optimising our surrogates implies the optimisation of the original generalisation bounds, (ii) instantiate this strategy to the framework of meta-learning, introducing a meta-objective offering a closed form expression for meta-gradient, (iii) illustrate our approach with numerical experiments inspired by an industrial biochemical problem.
title Learning via Surrogate PAC-Bayes
topic Machine Learning
url https://arxiv.org/abs/2410.10230