Statistics Papers

Document Type

Conference Paper

Date of this Version

2010

Publication Source

Proceedings of the 13th International Conference on Artificial Intelligence and Statistics

Volume

9

Start Page

381

Last Page

388

Abstract

The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions when the optimal parameter vector is sparse. This work characterizes a certain strong convexity property of general exponential families, which allows their generalization ability to be quantified. In particular, we show how this property can be used to analyze generic exponential families under L1 regularization.

Share

COinS
 

Date Posted: 27 November 2017

This document has been peer reviewed.