How good is a kernel when used as a similarity measure?

  • Authors:
  • Nathan Srebro

  • Affiliations:
  • Toyota Technological Institute-Chicago, IL and IBM Haifa Research Lab, Israel

  • Venue:
  • COLT'07 Proceedings of the 20th annual conference on Learning theory
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semidefinite kernels. We study the gap between the learning guarantees based on kernel-based learning, and those that can be obtained by using the kernel as a similarity function, which was left open by Balcan and Blum. We provide a significantly improved bound on how good a kernel function is when used as a similarity function, and extend the result also to the more practically relevant hinge-loss rather then zero-one-error-rate. Furthermore, we show that this bound is tight, and hence establish that there is in-fact a real gap between the traditional kernel-based notion of margin and the newer similarity-based notion.