Entropy concentration and the empirical coding game

P.D. Grünwald

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
1 Downloads (Pure)


We give a characterization of maximum entropy/minimum relative entropy inference by providing two 'strong entropy concentration' theorems. These theorems unify and generalize Jaynes''concentration phenomenon' and Van Campenhout and Cover's 'conditional limit theorem'. The theorems characterize exactly in what sense a prior distribution Q conditioned on a given constraint and the distribution (Xn)n ¿ N0 minimizing D(P ¿ Q) over all P satisfying the constraint are 'close' to each other. We then apply our theorems to establish the relationship between entropy concentration and a game-theoretic characterization of maximum entropy inference of Topsøe and others.
Original languageEnglish
Pages (from-to)374-392
JournalStatistica Neerlandica
Issue number3
Publication statusPublished - 2008


Dive into the research topics of 'Entropy concentration and the empirical coding game'. Together they form a unique fingerprint.

Cite this