Optimization with First-Order Surrogate Functions - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Optimization with First-Order Surrogate Functions

Résumé

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we provide a unified viewpoint for several first-order optimization techniques such as accelerated proximal gradient, block coordinate descent, or Frank-Wolfe algorithms. Second, we introduce a new incremental scheme that experimentally matches or outperforms state-of-the-art solvers for large-scale optimization problems typically arising in machine learning.
Fichier principal
Vignette du fichier
main.pdf (650.1 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00822229 , version 1 (14-05-2013)

Identifiants

Citer

Julien Mairal. Optimization with First-Order Surrogate Functions. ICML 2013 - International Conference on Machine Learning, Jun 2013, Atlanta, United States. pp.783-791. ⟨hal-00822229⟩
6441 Consultations
1574 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More