From Blackwell dominance in large samples to Rényi divergences and back again

From MaRDI portal
Publication:5012771

DOI10.3982/ECTA17548zbMATH Open1476.62025arXiv1906.02838OpenAlexW3120886835MaRDI QIDQ5012771FDOQ5012771


Authors: Xiaosheng Mu, Luciano Pomatto, Philipp Strack, Omer Tamuz Edit this on Wikidata


Publication date: 25 November 2021

Published in: Econometrica (Search for Journal in Brave)

Abstract: We study repeated independent Blackwell experiments; standard examples include drawing multiple samples from a population, or performing a measurement in different locations. In the baseline setting of a binary state of nature, we compare experiments in terms of their informativeness in large samples. Addressing a question due to Blackwell (1951), we show that generically an experiment is more informative than another in large samples if and only if it has higher Renyi divergences. We apply our analysis to the problem of measuring the degree of dissimilarity between distributions by means of divergences. A useful property of Renyi divergences is their additivity with respect to product distributions. Our characterization of Blackwell dominance in large samples implies that every additive divergence that satisfies the data processing inequality is an integral of Renyi divergences.


Full work available at URL: https://arxiv.org/abs/1906.02838




Recommendations





Cited In (2)





This page was built for publication: From Blackwell dominance in large samples to Rényi divergences and back again

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5012771)