$\ell_1$范数支持向量机的非渐近性分析
Non-asymptotic Analysis of $\ell_1$-norm Support Vector Machines
摘要:
带$\ell_1$惩罚的支持向量机(Support Vector Machines,SVM)在生物信息学和信号处理等领域成为分析具有稀疏约束的高维分类问题的标准工具。虽然支持向量机已被深入研究的文献中,本文有我们所知的第一个非渐近结果的性能$\ell_1$ -支持向量机在识别稀疏分类器。我们表明,$d$维$s$稀疏分类向量可以(以高概率)很好地近似只有$O(s\log(d))$高斯试验。证明中使用的方法包括测度集中和Banach空间中的概率。
英文摘要:
Support Vector Machines (SVM) with $\ell_1$ penalty became a standard tool in analysis of highdimensional classification problems with sparsity constraints in many applications including bioinformatics and signal processing. Although SVM have been studied intensively in the literature, this paper has to our knowledge first non-asymptotic results on the performance of $\ell_1$-SVM in identification of sparse classifiers. We show that a $d$-dimensional $s$-sparse classification vector can be (with high probability) well approximated from only $O(s\log(d))$ Gaussian trials. The methods used in the proof include concentration of measure and probability in Banach spaces.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。