A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

Résumé

We propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines the notions of smoothing and homotopy under the CGM framework, and provably achieves the optimal O(1/√k) convergence rate. We demonstrate that the same rate holds if the linear subproblems are solved approximately with additive or multiplicative error. Specific applications of the framework include the non-smooth minimization, semidefinite programming, and minimization with linear inclusion constraints over a compact domain. We provide numerical evidence to demonstrate the benefits of the new framework.
Fichier non déposé

Dates et versions

hal-02292460 , version 1 (19-09-2019)

Identifiants

  • HAL Id : hal-02292460 , version 1

Citer

Alp Yurtsever, Olivier Fercoq, Volkan Cevher, Francesco Locatello. A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming. International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. ⟨hal-02292460⟩
33 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More