Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints
Shai Shalev-Shwartz, Nati Srebro and Tong Zhang
Siam Journal on Optimization
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