catoni_draft2.pdf
ocatoni.perso.math.cnrs.fr · 8,939 words · saved by 1 readers
N/A
PAC-BAYESIAN SUPERVISED CLASSIFICATION (The thermodynamics of statistical learning) Olivier Catoni August 10, 2007 Abstract: This monograph deals with adaptive supervised classification, using tools borrowed from statistical mechanics and information theory, stemming from the PAC-Bayesian approach pioneered by David McAllester and applied to a conception of statistical learning theory forged by Vladimir Vapnik. Using convex analysis on the set of posterior probability measures, we show how to get local measures…
saved by
related reading
- [2407.19777] Revisiting Agnostic PAC Learningarxiv.org
- notes.pdfjingbol.web.illinois.edu
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- arxiv.org/pdf/1805.08522arxiv.org
- Learning to be Bayesian without Supervisionpapers.nips.cc
- Short Notes on Divergence Measuresdanilorezende.com
- RescaledKL.tmdanilorezende.com
- uncertain-modern-topics-in-uncertainty-estimation.pdfcalibration-tutorial.github.io
- An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
- 1011.0686arxiv.org
- empirical_bayes_without_prior_or_supervision_raphan.pdfcns.nyu.edu
- rakhlin_mathstat_sp24.pdfmit.edu