PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints
Shai Shalev-Shwartz, Nati Srebro and Tong Zhang
Siam Journal on Optimization Volume 20, Number 6, 2010.

Abstract

We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the resulting optimization problem is generally NP-hard, several approximation algorithms are considered. We analyze the performance of these algorithms, focusing on the characterization of the trade-off between accuracy and sparsity of the learned predictor in different scenarios.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:7139
Deposited By:Shai Shalev-Shwartz
Deposited On:06 March 2011