Dimension-free Information Concentration via Exp-Concavity

Information concentration of probability measures have important implications in learning theory. Recently, it is discovered that the information content of a log-concave distribution concentrates around their differential entropy, albeit with an unpleasant dependence on the ambient dimension. In this work, we prove that if the potentials of the log-concave distribution are exp-concave, which is a central notion for fast rates in online and statistical learning, then the concentration of information can be further improved to depend only on the exp-concavity parameter, and hence, it can be dimension independent. Central to our proof is a novel yet simple application of the variance Brascamp-Lieb inequality. In the context of learning theory, our concentration-of-information result immediately implies high-probability results to many of the previous bounds that only hold in expectation.

Presented at:
Algorithmic Learning Theory (ALT) 2018, Lanzarote, Spain, April 7-9, 2018

Note: The status of this file is: Anyone

 Record created 2018-02-26, last modified 2020-04-20

Download fulltextPDF Download fulltextPDF (PDFA)
Rate this document:

Rate this document:
(Not yet reviewed)