Tighter PAC-Bayes bounds through distribution-dependent priors

DOI10.1016/J.TCS.2012.10.013MaRDI QIDQ1939259zbMATH OpenOpenAlexFDO

Authors Guy Lever, François Laviolette, John Shawe-Taylor

Publication date 4 March 2013

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2012.10.013

zbMATH Keywords

exponential weights algorithmlocalized boundsPAC-Bayessemi-supervised learningstatistical learning theorySVM

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• PAC-Bayes bounds with data dependent priors
• Data dependent priors in PAC-Bayes bounds
• Distribution-Dependent PAC-Bayes Priors
• A PAC-Bayes Bound for Tailored Density Estimation
• A strongly quasiconvex PAC-Bayesian bound
• PAC-Bayesian bounds for randomized empirical risk minimizers
• scientific article; zbMATH DE number 7219345
• PAC-Bayes bounds for supervised classification
• Simplified PAC-Bayesian margin bounds.
• Some PAC-Bayesian theorems

Cited in

(18)

• Simpler PAC-Bayesian bounds for hostile data
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• Some PAC-Bayesian theorems
• Learning a priori constrained weighted majority votes
• Combining PAC-Bayesian and generic chaining bounds
• scientific article; zbMATH DE number 5957470 (Why is no real title available?)
• scientific article; zbMATH DE number 7219345 (Why is no real title available?)
• Data dependent priors in PAC-Bayes bounds
• A strongly quasiconvex PAC-Bayesian bound
• Distribution-Dependent PAC-Bayes Priors
• A PAC-Bayes Bound for Tailored Density Estimation
• scientific article; zbMATH DE number 7626742 (Why is no real title available?)
• PAC-Bayes bounds with data dependent priors
• User-friendly Introduction to PAC-Bayes Bounds
• Generalized geographically weighted regression model within a modularized Bayesian framework
• Generalization bounds: perspectives from information theory and PAC-Bayes
• Learning-to-optimize with PAC-Bayesian guarantees: theoretical considerations and practical implementation
• PAC-Bayesian bounds for randomized empirical risk minimizers

This page was built for publication: Tighter PAC-Bayes bounds through distribution-dependent priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1939259)