REGULARIZATION IN KERNEL LEARNING

• 成果类型: Article
• 署名作者: Mendelson, Shahar; Neeman, Joseph
• 署名单位: Australian National University; Technion Israel Institute of Technology; University of California System; University of California Berkeley
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/09-AOS728
• 发表日期: 2010
• 页码: 526-565
• 关键词: Support vector machines; Oracle Inequalities; entropy numbers; fast rates; performance; error; Operators

摘要

Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one can use a regularization term that grows significantly slower than the standard quadratic growth in the RKHS norm.