Gradient Projection and Conditional Gradient Methods for Constrained Nonconvex Minimization
Year: 2020
Type: article
Abstract: Minimization of a smooth function on a sphere or, more generally, on a smooth manifold, is the simplest non-convex optimization problem. It has a lot of applications. Our goal is to propose a version of the gradient projection algorithm for its solution and to obtain results that guarantee convergence of the algorithm under some minimal natural assumptions. We use the Ležanski-Polyak-Lojasiewicz condition on a manifold to prove the global linear convergence of the algorithm. Another method well fitted for the problem is the conditional gradient (Frank-Wolfe) algorithm. We examine some conditions which guarantee global convergence of full-step version of the method with linear rate.
Authors: M. V. Balashov, B. T. Polyak, A. A. Tremba
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Russian Science Foundation
Awards: G3118402170, G5106821595
OpenAlex ID: W2956019824
