Optimal Bregman prediction and Jensen's equality

Arindam Banerjee, Xin Guo, Hui Wang

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations


We provide necessary and sufficient conditions for general loss functions under which the conditional expectation is the unique optimal predictor of a random variable. Further, using such loss functions, we give an exact characterization of the difference between the two sides of Jensen's inequality.

Original languageEnglish (US)
Number of pages1
JournalIEEE International Symposium on Information Theory - Proceedings
StatePublished - Oct 20 2004
EventProceedings - 2004 IEEE International Symposium on Information Theory - Chicago, IL, United States
Duration: Jun 27 2004Jul 2 2004


Dive into the research topics of 'Optimal Bregman prediction and Jensen's equality'. Together they form a unique fingerprint.

Cite this