文献类型：期刊文献

英文题名：Error analysis of the kernel regularized regression based on refined convex losses and RKBSs

作者：Sheng, Baohuai[1];Zuo, Lan[1]

机构：[1]Shaoxing Univ, Dept Appl Stat, Shaoxing 312000, Peoples R China

年份：2021

卷号：19

期号：05

外文期刊名：INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING

收录：SCI-EXPANDED(收录号：WOS:000707381400005)、、EI(收录号：20211810299138)、Scopus(收录号：2-s2.0-85104961717)、WOS

基金：This work is supported partially by the NSF (Project No. 61877039), the NSFC/RGC Joint Research Scheme (Project No. 12061160462 and N_CityU102/20) of China and the NSF (Project No. LY19F020013) of Zhejiang Province.

语种：英文

外文关键词：Reproducing kernel Banach space; kernel regularized regression; uniformly convex function; uniformly smooth function; uniformly convex space

外文摘要：In this paper, we bound the errors of kernel regularized regressions associating with 2-uniformly convex two-sided RKBSs and differentiable sigma(t) = vertical bar t vertical bar(p)/p (1 <= p <= 2) uniformly smooth losses. In particular, we give learning rates for the learning algorithm with loss V-p(t) = vertical bar t vertical bar(p)/p (1 < p <= 2). Also, we show a probability inequality and with which provide the error bounds for kernel regularized regression with loss V-q(t) = vertical bar t vertical bar(q)/q (q > 2). The discussions are comprehensive applications of the uniformly smooth function theory, the uniformly convex function theory and uniformly convex space theory.