Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity
Machine Learning
2015-05-19 v2 Machine Learning
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, such as when there is some sparsity pattern of the optimal parameter. This work characterizes a certain strong convexity property of general exponential families, which allow their generalization ability to be quantified. In particular, we show how this property can be used to analyze generic exponential families under L_1 regularization.
Keywords
Cite
@article{arxiv.0911.0054,
title = {Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity},
author = {Sham M. Kakade and Ohad Shamir and Karthik Sridharan and Ambuj Tewari},
journal= {arXiv preprint arXiv:0911.0054},
year = {2015}
}
Comments
Errata added. Incorrect claim about cumulants of the Bernoulli distribution fixed