From epsilon-Entropy to KL-Complexity: Analysis of Minimum Information Complexity Density Estimation

We extend the concept of epsilon-entropy to include randomized density estimation methods. Based on this extension, we develop a general information theoretical inequality that measures the statistical complexity of some deterministic and randomized density estimators. Consequences of the new inequality will be presented. In particular, we show that this technique can effortlessly lead to substantial improvements of some classical results concerning the convergence of minimum description length (MDL) and Bayesian posterior distributions. Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.

By: Tong Zhang

Published in: RC22980 in 2003


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .