An information-theoretic proof of a finite de finetti theorem
View / Open Files
Publication Date
2021-01-01Journal Title
Electronic Communications in Probability
ISSN
1083-589X
Publisher
Institute of Mathematical Statistics
Volume
26
Issue
none
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Gavalakis, L., & Kontoyiannis, I. (2021). An information-theoretic proof of a finite de finetti theorem. Electronic Communications in Probability, 26 (none) https://doi.org/10.1214/21-ECP428
Abstract
A finite form of de Finetti's representation theorem is established using
elementary information-theoretic tools: The distribution of the first $k$
random variables in an exchangeable binary vector of length $n\geq k$ is close
to a mixture of product distributions. Closeness is measured in terms of the
relative entropy and an explicit bound is provided.
Keywords
cs.IT, cs.IT, math.IT, math.PR
Identifiers
External DOI: https://doi.org/10.1214/21-ECP428
This record's URL: https://www.repository.cam.ac.uk/handle/1810/332110
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.