Tight PAC-Bayesian risk certificates for contrastive learning

DOI10.1137/24M1715283MaRDI QIDQ6876745zbMATH OpenFDO

Authors Anna van Elst, Debarghya Ghoshdastidar

Publication date 12 January 2026

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1715283

zbMATH Keywords

PAC-Bayesian theoryrepresentation learningself-supervised learning

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Contrastive learning, multi-view redundancy, and linear models
• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 5544465 (Why is no real title available?)
• scientific article; zbMATH DE number 7626742 (Why is no real title available?)
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• PAC-Bayesian stochastic model selection
• Simplified PAC-Bayesian margin bounds.
• The collected works of Wassily Hoeffding. Ed. by N. I. Fisher and P. K. Sen

This page was built for publication: Tight PAC-Bayesian risk certificates for contrastive learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6876745)