Convergence rates of the stochastic alternating algorithm for bi-objective optimization
Abstract
Stochastic alternating algorithms for bi-objective optimization are considered when optimizing two conflicting functions for which optimization steps have to be applied separately for each function. Such algorithms consist of applying a certain number of steps of gradient or subgradient descent on each single objective at each iteration. In this paper, we show that stochastic alternating algorithms achieve a sublinear convergence rate of , under strong convexity, for the determination of a minimizer of a weighted-sum of the two functions, parameterized by the number of steps applied on each of them. An extension to the convex case is presented for which the rate weakens to . These rates are valid also in the non-smooth case. Importantly, by varying the proportion of steps applied to each function, one can determine an approximation to the Pareto front.
Cite
@article{arxiv.2203.10605,
title = {Convergence rates of the stochastic alternating algorithm for bi-objective optimization},
author = {Suyun Liu and Luis Nunes Vicente},
journal= {arXiv preprint arXiv:2203.10605},
year = {2023}
}