Total Stability of SVMs and Localized SVMs

Helmut Köhler,Andreas Christmann

arXiv (Cornell University)(2021)

引用 0|浏览0
暂无评分
摘要
Regularized kernel-based methods such as support vector machines (SVMs) typically depend on the underlying probability measure $\mathrm{P}$ (respectively an empirical measure $\mathrm{D}_n$ in applications) as well as on the regularization parameter $\lambda$ and the kernel $k$. Whereas classical statistical robustness only considers the effect of small perturbations in $\mathrm{P}$, the present paper investigates the influence of simultaneous slight variations in the whole triple $(\mathrm{P},\lambda,k)$, respectively $(\mathrm{D}_n,\lambda_n,k)$, on the resulting predictor. Existing results from the literature are considerably generalized and improved. In order to also make them applicable to big data, where regular SVMs suffer from their super-linear computational requirements, we show how our results can be transferred to the context of localized learning. Here, the effect of slight variations in the applied regionalization, which might for example stem from changes in $\mathrm{P}$ respectively $\mathrm{D}_n$, is considered as well.
更多
查看译文
关键词
svms,total stability
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要