Penalized empirical relaxed greedy algorithm for fixed design Gaussian regression

• DOI: 10.1142/s0219691316500193
• Publication Date: 2016-04-26T09:22:16Z
• Authors: Chen Chen; Na Chen
• Keywords: Regularization

Compared with [Formula: see text]-regularization algorithm, greedy algorithm has great advantage in computational complexity. In this paper, we consider the penalized empirical relaxed and analyze its efficiency fixed design Gaussian regression problem. Through a careful analysis, provide oracle inequalities case of finite infinite dictionary, respectively via choosing appropriate number iterations. Relying on those inequalities, obtain learning rate when target function lies convex hull dictionary. Our results show that error text] decay, which is near optimal convergence literature.