An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration

Abstract : We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic variance-reduced gradient descent algorithm (SVRG) and other randomized incremental optimization algorithms. QNing is also compatible with composite objectives, meaning that it has the ability to provide exactly sparse solutions when the objective involves a sparsity-inducing regularization. When combined with limited-memory BFGS rules, QNing is particularly effective to solve high-dimensional optimization problems, while enjoying a worst-case linear convergence rate for strongly convex problems. We present experimental results where QNing gives significant improvements over competing methods for training machine learning methods on large samples and in high dimensions.
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

https://hal.inria.fr/hal-01376079
Contributeur : Julien Mairal <>
Soumis le : vendredi 20 juillet 2018 - 15:50:30
Dernière modification le : vendredi 7 septembre 2018 - 16:24:30

Fichiers

quickening_arxiv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01376079, version 3
  • ARXIV : 1610.00960

Collections

Citation

Hongzhou Lin, Julien Mairal, Zaid Harchaoui. An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration. 2018. 〈hal-01376079v3〉

Partager

Métriques

Consultations de la notice

120

Téléchargements de fichiers

107