paper

The exact worst-case convergence rate of the gradient method with fixed step lengths for L-smooth functions

arXiv:2104.05468

Abstract

In this paper, we study the convergence rate of the gradient (or steepest descent) method with fixed step lengths for finding a stationary point of an -smooth function. We establish a new convergence rate, and show that the bound may be exact in some cases, in particular when all step lengths lie in the interval . In addition, we derive an optimal step length with respect to the new bound.