English

Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior

Machine Learning 2019-03-28 v2 Machine Learning

Abstract

We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory. While the primary goal of RFF is to approximate a kernel, we look at the Fourier transform as a prior distribution over trigonometric hypotheses. It naturally suggests learning a posterior on these hypotheses. We derive generalization bounds that are optimized by learning a pseudo-posterior obtained from a closed-form expression. Based on this study, we consider two learning strategies: The first one finds a compact landmarks-based representation of the data where each landmark is given by a distribution-tailored similarity measure, while the second one provides a PAC-Bayesian justification to the kernel alignment method of Sinha and Duchi (2016).

Keywords

Cite

@article{arxiv.1810.12683,
  title  = {Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior},
  author = {Gaël Letarte and Emilie Morvant and Pascal Germain},
  journal= {arXiv preprint arXiv:1810.12683},
  year   = {2019}
}

Comments

Published at AISTATS 2019

R2 v1 2026-06-23T04:57:32.220Z