pith. sign in

arxiv: 1610.07193 · v2 · pith:Q3VIVSVZnew · submitted 2016-10-23 · 📊 stat.ML · math.ST· stat.TH

Simpler PAC-Bayesian Bounds for Hostile Data

classification 📊 stat.ML math.STstat.TH
keywords boundspac-bayesiandivergencehostilelearningdatadistributiongeneral
0
0 comments X
read the original abstract

PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution $\rho$ to its empirical risk and to its Kullback-Leibler divergence with respect to some prior distribution $\pi$. Unfortunately, most of the available bounds typically rely on heavy assumptions such as boundedness and independence of the observations. This paper aims at relaxing these constraints and provides PAC-Bayesian learning bounds that hold for dependent, heavy-tailed observations (hereafter referred to as \emph{hostile data}). In these bounds the Kullack-Leibler divergence is replaced with a general version of Csisz\'ar's $f$-divergence. We prove a general PAC-Bayesian bound, and show how to use it in various hostile settings.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.