Home » Publication » 27074

Dettaglio pubblicazione

2021, MATHEMATICAL PROGRAMMING, Pages 1-45

Parallel random block-coordinate forward–backward algorithm: a unified convergence analysis (01a Articolo in rivista)

Salzo S., Villa S.

We study the block-coordinate forward–backward algorithm in which the blocks are updated in a random and possibly parallel manner, according to arbitrary probabilities. The algorithm allows different stepsizes along the block-coordinates to fully exploit the smoothness properties of the objective function. In the convex case and in an infinite dimensional setting, we establish almost sure weak convergence of the iterates and the asymptotic rate o(1/n) for the mean of the function values. We derive linear rates under strong convexity and error bound conditions. Our analysis is based on an abstract convergence principle for stochastic descent algorithms which allows to extend and simplify existing results.
Gruppo di ricerca: Continuous Optimization
keywords
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma