Entropy concentration and the empirical coding game
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 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. Copyright (c) 2008 The Author. Journal compilation (c) 2008 VVS.
If you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
As the access to this document is restricted, you may want to look for a different version under "Related research" (further below) or search for a different version of it.
Volume (Year): 62 (2008)
Issue (Month): 3 ()
|Contact details of provider:|| Web page: http://www.blackwellpublishing.com/journal.asp?ref=0039-0402|
|Order Information:||Web: http://www.blackwellpublishing.com/subs.asp?ref=0039-0402|
When requesting a correction, please mention this item's handle: RePEc:bla:stanee:v:62:y:2008:i:3:p:374-392. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Wiley-Blackwell Digital Licensing)or (Christopher F. Baum)
If references are entirely missing, you can add them using this form.