Local Convergence Properties of Douglas–Rachford and Alternating Direction Method of Multipliers

Jingwei Liang (1) , Jalal M. Fadili (1) , Gabriel Peyré (2)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 MOKAPLAN - Méthodes numériques pour le problème de Monge-Kantorovich et Applications en sciences sociales

The Douglas–Rachford and alternating direction method of multipliers are two proximal splitting algorithms designed to minimize the sum of two proper lower semi-continuous convex functions whose proximity operators are easy to compute. The goal of this work is to understand the local linear convergence behaviour of Douglas–Rachford (resp. alternating direction method of multipliers) when the involved functions (resp. their Legendre-Fenchel conjugates) are moreover partly smooth. More precisely, when the two functions (resp. their conjugates) are partly smooth relative to their respective smooth submanifolds, we show that Douglas–Rachford (resp. alternating direction method of multipliers) (i) identifies these manifolds in finite time; (ii) enters a local linear convergence regime. When both functions are locally polyhe-dral, we show that the optimal convergence radius is given in terms of the cosine of the Friedrichs angle between the tangent spaces of the identified submanifolds. Under polyhedrality of both functions, we also provide conditions sufficient for finite convergence. The obtained results are illustrated by several concrete examples and supported by numerical experiments.

Mots clés: Identification · Local Linear Convergence; Partial Smoothness; Finite Activity; ADMM; Douglas–Rachford

Domaines: Optimisation et contrôle [math.OC]; Statistiques [math.ST]; Analyse fonctionnelle [math.FA]; Analyse numérique [math.NA]; Machine Learning [stat.ML]; Théorie [stat.TH]; Théorie de l'information [cs.IT]; Traitement du signal et de l'image [eess.SP]

Jingwei Liang, Jalal M. Fadili, Gabriel Peyré. Local Convergence Properties of Douglas–Rachford and Alternating Direction Method of Multipliers. Journal of Optimization Theory and Applications, 2017, 172 (3), pp.874-913. ⟨10.1007/s10957-017-1061-z⟩. ⟨hal-01658848⟩