A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning

Konstantin Mishchenko (1) , Franck Iutzeler (2) , Jérôme Malick (2) , Massih-Reza Amini (3)

1 KAUST - King Abdullah University of Science and Technology [Saudi Arabia]
2 DAO - Données, Apprentissage et Optimisation
3 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]

Distributed learning aims at computing high-quality models by training over scattered data. This covers a diversity of scenarios, including computer clusters or mobile agents. One of the main challenges is then to deal with heterogeneous machines and unreliable communications. In this setting, we propose and analyze a flexible asynchronous optimization algorithm for solving nonsmooth learning problems. Unlike most existing methods, our algorithm is adjustable to various levels of communication costs, machines computational powers, and data distribution evenness. We prove that the algorithm converges linearly with a fixed learning rate that does not depend on communication delays nor on the number of machines. Although long delays in communication may slow down performance, no delay can break convergence.

Domaines: Calcul parallèle, distribué et partagé [cs.DC]; Machine Learning [stat.ML]; Optimisation et contrôle [math.OC]

Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick, Massih-Reza Amini. A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning. International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.3587-3595. ⟨hal-01996562⟩