The Cyclic Block Conditional Gradient Method for Convex Optimization Problems - Archive ouverte HAL
Article Dans Une Revue SIAM Journal on Optimization Année : 2015

The Cyclic Block Conditional Gradient Method for Convex Optimization Problems

Résumé

In this paper we study the convex problem of optimizing the sum of a smooth function and a compactly supported nonsmooth term with a specific separable form. We analyze the block version of the generalized conditional gradient method when the blocks are chosen in a cyclic order. A global sublinear rate of convergence is established for two different stepsize strategies commonly used in this class of methods. Numerical comparisons of the proposed method to both the classical conditional gradient algorithm and its random block version demonstrate the effectiveness of the cyclic block update rule.

Dates et versions

hal-01491541 , version 1 (17-03-2017)

Identifiants

Citer

Amir Beck, Edouard Pauwels, Shoham Sabach. The Cyclic Block Conditional Gradient Method for Convex Optimization Problems. SIAM Journal on Optimization, 2015, 4, pp.2024-2049. ⟨10.1137/15M1008397⟩. ⟨hal-01491541⟩
151 Consultations
0 Téléchargements

Altmetric

Partager

More