Accelerated Gradient Methods with Memory

Abstract

A set of accelerated first order algorithms with memory are proposed for minimising strongly convex functions. The algorithms are differentiated by their use of the iterate history for the gradient step. The increased convergence rate of the proposed algorithms comes at the cost of robustness, a problem that is resolved by a switching controller based upon adaptive restarting. Several numerical examples highlight the benefits of the proposed approach over the fast gradient method. For example, it is shown that these gradient based methods can minimise the Rosenbrock banana function to $7.58\times 10^{-12}$ in 43 iterations from an initial condition of $(-1,1)$.

10 pages. 10 figures