paper-with-me

홈 › Papers

On change of measure inequalities for $f$-divergences

2022-02-11 · Antoine Picard-Weibel, Benjamin Guedj

We propose new change of measure inequalities based on $f$-divergences (of which the Kullback-Leibler divergence is a particular case). Our strategy relies on combining the Legendre transform of $f$-divergences and the Young-Fenchel inequality. By exploiting these new change of measure inequalities, we derive new PAC-Bayesian generalisation bounds with a complexity involving $f$-divergences, and holding in mostly unchartered settings (such as heavy-tailed losses). We instantiate our results for the most popular $f$-divergences.

📄 PDF Abstract BibTeX arXiv:2202.05568

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation

2020-02-25 · Yuki Ohnishi, Jean Honorio

We introduce several novel change of measure inequalities for two families of divergences: $f$-divergences and $\alpha$-divergences. We show how the variational representation for $f$-divergences leads to novel change of…

Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities

2026-02-08 · Yanxiao Liu, Yijun Fan, Deniz Gündüz arxiv

Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic guarantees in learning theory, informati…

Sharp Inequalities for $f$-divergences

2013-02-02 · Adityanand Guntuboyina, Sujayam Saha, Geoffrey Schiebinger

$f$-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullbac…

From Generalisation Error to Transportation-cost Inequalities and Back

2022-02-08 · Amedeo Roberto Esposito, Michael Gastpar

In this work, we connect the problem of bounding the expected generalisation error with transportation-cost inequalities. Exposing the underlying pattern behind both approaches we are able to generalise them and go beyon…

Non-Linear Strong Data-Processing for Quantum Hockey-Stick Divergences

2025-12-18 · Theshani Nuradha, Ian George, Christoph Hirche arxiv

Data-processing is a desired property of classical and quantum divergences and information measures. In information theory, the contraction coefficient measures how much the distinguishability of quantum states decreases…