In this paper, we study the convergence properties of a randomized block-coordinate descent algorithm for the minimization of a composite convex objective function, where the block-coordinates are updated asynchronously and randomly according to an arbitrary probability distribution. We prove that the iterates generated by the algorithm form a stochastic quasi-Fejér sequence and thus converge almost surely to a minimizer of the objective function. Moreover, we prove a general sublinear rate of convergence in expectation for the function values and a linear rate of convergence in expectation under an error bound condition of Tseng type. Under the same condition strong convergence of the iterates is provided as well as their linear convergence rate.
2023, COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, Pages -
Convergence of an asynchronous block-coordinate forward-backward algorithm for convex composite optimization (01a Articolo in rivista)
Traoré Cheik, Salzo Saverio, Villa Silvia
Gruppo di ricerca: Continuous Optimization