English

Optimality Implies Kernel Sum Classifiers are Statistically Efficient

Machine Learning 2019-06-04 v2 Machine Learning

Abstract

We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typical learning theoretic results which hold for all (potentially suboptimal) classifiers. Our work also justifies assumptions made in prior work on multiple kernel learning. As a byproduct of our analysis, we also provide a new form of Rademacher complexity for hypothesis classes containing only optimal classifiers.

Keywords

Cite

@article{arxiv.1901.09087,
  title  = {Optimality Implies Kernel Sum Classifiers are Statistically Efficient},
  author = {Raphael Arkady Meyer and Jean Honorio},
  journal= {arXiv preprint arXiv:1901.09087},
  year   = {2019}
}