pith. sign in

arxiv: 1606.09365 · v2 · pith:DXSFVE5Cnew · submitted 2016-06-30 · 🧮 math.OC

On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions

classification 🧮 math.OC
keywords gradientconvexexactworst-casemethodsearchcomplexitydescent
0
0 comments X
read the original abstract

We consider the gradient (or steepest) descent method with exact line search applied to a strongly convex function with Lipschitz continuous gradient. We establish the exact worst-case rate of convergence of this scheme, and show that this worst-case behavior is exhibited by a certain convex quadratic function. We also give the tight worst-case complexity bound for a noisy variant of gradient descent method, where exact line-search is performed in a search direction that differs from negative gradient by at most a prescribed relative tolerance. The proofs are computer-assisted, and rely on the resolutions of semidefinite programming performance estimation problems as introduced in the paper [Y. Drori and M. Teboulle. Performance of first-order methods for smooth convex minimization: a novel approach. Mathematical Programming, 145(1-2):451-482, 2014].

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.