Concentration inequalities for the empirical distribution of discrete distributions: beyond the method of types

DOI10.1093/imaiai/iaz025zbMath1473.60047arXiv1809.06522OpenAlexW2989871066WikidataQ127229358 ScholiaQ127229358MaRDI QIDQ5006541

Jay Mardia, Ervin Tánczos, Tsachy Weissman, Jiantao Jiao, Robert D. Nowak

Publication date: 16 August 2021

Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.06522

zbMATH Keywords

empirical distributionSanov's theoremconcentration inequalitiesKL divergencemethod of types\(L_1\) deviation inequalities

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Large deviations (60F10) Measures of information, entropy (94A17)

Related Items

Robust Markov Decision Processes with Data-Driven, Distance-Based Ambiguity Sets ⋮ Optimal non-asymptotic concentration of centered empirical relative entropy in the high-dimensional regime