English

Learning rates for classification with Gaussian kernels

Machine Learning 2017-10-06 v3 Optimization and Control Machine Learning

Abstract

This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, provided the regression function is smooth. Our second result shows that, for a large number of loss functions, under some Tsybakov noise assumption, if the regression function is infinitely smooth, then SVM with Gaussian kernel can achieve the learning rate of order m1m^{-1}, where mm is the number of samples.

Keywords

Cite

@article{arxiv.1702.08701,
  title  = {Learning rates for classification with Gaussian kernels},
  author = {Shao-Bo Lin and Jinshan Zeng and Xiangyu Chang},
  journal= {arXiv preprint arXiv:1702.08701},
  year   = {2017}
}

Comments

This paper has been accepted by Neural Computation

R2 v1 2026-06-22T18:30:35.956Z