Tighter PAC-Bayes bounds through distribution-dependent priors

DOI10.1016/j.tcs.2012.10.013zbMath1277.68233OpenAlexW1999376700MaRDI QIDQ1939259

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

statistical learning theorySVMsemi-supervised learninglocalized boundsPAC-Bayesexponential weights algorithm

Mathematics Subject Classification ID

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

Related Items (4)

Local Rademacher complexity: sharper risk bounds with and without unlabeled samples ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ Unnamed Item ⋮ Learning a priori constrained weighted majority votes

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