Sciweavers

Share
SIAMJO
2010

Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints

9 years 1 months ago
Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints
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.
Shai Shalev-Shwartz, Nathan Srebro, Tong Zhang
Added 21 May 2011
Updated 21 May 2011
Type Journal
Year 2010
Where SIAMJO
Authors Shai Shalev-Shwartz, Nathan Srebro, Tong Zhang
Comments (0)
books