This is an announcement for the paper "Reproducing kernel Banach spaces with the l1 norm II: Error analysis for regularized least square regression" by Guohui Song, Haizhang Zhang.
Abstract: A typical approach in estimating the learning rate of a regularized learning scheme is to bound the approximation error by the sum of the sampling error, the hypothesis error and the regularization error. Using a reproducing kernel space that satisfies the linear representer theorem brings the advantage of discarding the hypothesis error from the sum automatically. Following this direction, we illustrate how reproducing kernel Banach spaces with the l1 norm can be applied to improve the learning rate estimate of l1-regularization in machine learning.
Archive classification: stat.ML cs.LG math.FA
Submitted from: zhhaizh2@sysu.edu.cn
The paper may be downloaded from the archive by web browser from URL
http://front.math.ucdavis.edu/1101.4439
or