Advanced Search

Query:

Fill in the form and click »Search«...

Format:

Display: entries per page entries

Zbl 1228.62044
Feng, Yun-Long; Lv, Shao-Gao
Unified approach to coefficient-based regularized regression. (English)
[J] Comput. Math. Appl. 62, No. 1, 506-515 (2011). ISSN 0898-1221

Summary: We consider the coefficient-based regularized least-squares regression problem with the $l^{q}$-regularizer ($1\le q\le 2$) and data dependent hypothesis spaces. Algorithms for data dependent hypothesis spaces perform well with the property of flexibility. We conduct a unified error analysis by a stepping stone technique. An empirical covering number technique is also employed in our study to improve sample errors. Comparing with existing results, we make a few improvements: First, we obtain a significantly sharper learning rate that can be arbitrarily close to $O(m^{ - 1})$ under reasonable conditions, which is regarded as the best learning rate in learning theory. Second, our results cover the case $q=1$, which is novel. Finally, our results hold under very general conditions.

MSC 2000:: *62G08 Nonparametric regression
68T99 Artificial intelligence

Keywords: data dependent hypothesis spaces; $l^{q}$-regularizer; $\ell ^{2}$-empirical covering number; learning rates

Comment on this Item PDF MathML XML ASCII DVI PS BibTeX Online Ordering Article Journal

	Scientific prize winners of the ICM 2010
	Overhang
	Lie groups, physics and geometry. An introduction for physicists, engineers and chemists.

Advanced Search

Zentralblatt MATH Berlin [Germany]