Infinite-dimensional gradient-based descent for alpha-divergence minimisation - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Infinite-dimensional gradient-based descent for alpha-divergence minimisation

Résumé

This paper introduces the $(\alpha, \Gamma)$-descent, an iterative algorithm which operates on measures and performs $\alpha$-divergence minimisation in a Bayesian framework. This gradient-based procedure extends the commonly-used variational approximation by adding a prior on the variational parameters in the form of a measure. We prove that for a rich family of functions $\Gamma$, this algorithm leads at each step to a systematic decrease in the $\alpha$-divergence and derive convergence results. Our framework recovers the Entropic Mirror Descent algorithm and provides an alternative algorithm that we call the Power Descent. Moreover, in its stochastic formulation, the $(\alpha, \Gamma)$-descent allows to optimise the mixture weights of any given mixture model without any information on the underlying distribution of the variational parameters. This renders our method compatible with many choices of parameters updates and applicable to a wide range of Machine Learning tasks. We demonstrate empirically on both toy and real-world examples the benefit of using the Power descent and going beyond the Entropic Mirror Descent framework, which fails as the dimension grows.
Fichier principal
Vignette du fichier
DaudelDoucPortier2020.pdf (1002.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02614605 , version 1 (21-05-2020)
hal-02614605 , version 2 (15-10-2020)
hal-02614605 , version 3 (27-04-2023)

Identifiants

Citer

Kamélia Daudel, Randal Douc, François Portier. Infinite-dimensional gradient-based descent for alpha-divergence minimisation. 2020. ⟨hal-02614605v2⟩
646 Consultations
239 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More