Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

144

SIAMJO
2010

125views more SIAMJO 2010»

Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints

14 years 10 months ago

Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints

Download www.cs.huji.ac.il

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

Real-time Traffic

Expected Loss | Linear Predictor | SIAMJO 2010 | Sparsity |

claim paper

Related Content

» Efficient image reconstruction under sparsity constraints with application to MRI and biol...

» A General Framework for Structured Sparsity via Proximal Optimization

» Convex and Network Flow Optimization for Structured Sparsity

» Sparsity penalties in dynamical system estimation

» Semiblind SpeechMusic Separation Using Sparsity and Continuity Priors

» Feature Selection for Unsupervised and Supervised Inference the Emergence of Sparsity in a...

» Reduced complexity models in the identification of dynamical networks Links with sparsific...

» Efficient and Numerically Stable Sparse Learning

» LargeScale ManyClass Learning

Post Info
More Details (n/a)

Added	21 May 2011
Updated	21 May 2011
Type	Journal
Year	2010
Where	SIAMJO
Authors	Shai Shalev-Shwartz, Nathan Srebro, Tong Zhang

Comments (0)