Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization

Résumé

We propose a new first-order optimisation algorithm to solve high-dimensional non-smooth composite minimisation problems. Typical examples of such problems have an objective that decomposes into a non-smooth empirical risk part and a non-smooth regularisation penalty. The proposed algorithm, called Semi-Proximal Mirror-Prox, leverages the Fenchel-type representation of one part of the objective while handling the other part of the objective via linear minimization over the domain. The algorithm stands in contrast with more classical proximal gradient algorithms with smoothing, which require the computation of proximal operators at each iteration and can therefore be impractical for high-dimensional problems. We establish the theoretical convergence rate of Semi-Proximal Mirror-Prox, which exhibits the optimal complexity bounds, i.e.O(1/∊2), for the number of calls to linear minimization oracle. We present promising experimental results showing the interest of the approach in comparison to competing methods.
Fichier principal
Vignette du fichier
main-rpt.pdf (499.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01171567 , version 1 (05-07-2015)

Identifiants

  • HAL Id : hal-01171567 , version 1

Citer

Niao He, Zaid Harchaoui. Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization. NIPS - Advances in Neural Information Processing Systems, Dec 2015, Montreal, Canada. pp.3411-3419. ⟨hal-01171567⟩
606 Consultations
250 Téléchargements

Partager

Gmail Facebook X LinkedIn More