Titre :

Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior

Auteur(s) :

Letarte, Gaël [Auteur]
Département d'informatique et de génie logiciel [Québec]
Morvant, Emilie [Auteur]
Laboratoire Hubert Curien [LabHC]
Germain, Pascal [Auteur]
MOdel for Data Analysis and Learning [MODAL]

Titre de la manifestation scientifique :

The 22nd International Conference on Artificial Intelligence and Statistics

Ville :

Naha

Pays :

Japon

Date de début de la manifestation scientifique :

2019-04-16

Titre de la revue :

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 2019,

Date de publication :

2019

Mot(s)-clé(s) en anglais :

Kernel Approximation
Random Fourier Features
PAC-Bayesian Theory
Kernel Learning

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

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 ...
Lire la suite >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).Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Une Perspective PAC-Bayésienne de l'Apprentissage de Représentations

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL