A New Primal-Dual Algorithm for a Class of Nonlinear Compositional Convex Optimization Problems
Abstract
We develop a novel primal-dual algorithm to solve a class of nonsmooth and nonlinear compositional convex minimization problems, which covers many existing and brand-new models as special cases. Our approach relies on a combination of a new nonconvex potential function, Nesterov's accelerated scheme, and an adaptive parameter updating strategy. Our algorithm is single-loop and has low per-iteration complexity. Under only general convexity and mild assumptions, our algorithm achieves convergence rates through three different criteria: primal objective residual, dual objective residual, and primal-dual gap, where is the iteration counter. Our rates are both ergodic (i.e., on an averaging sequence) and non-ergodic (i.e., on the last-iterate sequence). These convergence rates can be accelerated up to if only one objective term is strongly convex (or equivalently, its conjugate is -smooth). To the best of our knowledge, this is the first algorithm achieving optimal rates on the primal last-iterate sequence for nonlinear compositional convex minimization. As a by-product, we specify our algorithm to solve a general convex cone constrained program with both ergodic and non-ergodic rate guarantees. We test our algorithms and compare them with two recent methods on a binary classification and a convex-concave game model.
Cite
@article{arxiv.2006.09263,
title = {A New Primal-Dual Algorithm for a Class of Nonlinear Compositional Convex Optimization Problems},
author = {Yuzixuan Zhu and Deyi Liu and Quoc Tran-Dinh},
journal= {arXiv preprint arXiv:2006.09263},
year = {2021}
}
Comments
26 pages, 2 figures, 1 table