pith. sign in

arxiv: 1810.12683 · v2 · pith:WXLS7SHPnew · submitted 2018-10-30 · 📊 stat.ML · cs.LG

Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior

classification 📊 stat.ML cs.LG
keywords kernellearningfourierhypothesesmethodpac-bayesianpriortransform
0
0 comments X
read the original 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).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.