Averaged Heavy-Ball Method

Published in Computer Research and Modeling, 2022

PDF, Cite, arXiv, Computer Research and Modeling


Heavy-Ball method (HB) is known for its simplicity in implementation and practical efficiency. However, as with other momentum methods, it has non-monotone behavior, and for optimal parameters, the method suffers from the so-called peak effect. To address this issue, in this paper, we consider an averaged version of Heavy-Ball method (AHB). We show that for quadratic problems AHB has a smaller maximal deviation from the solution than HB. Moreover, for general convex and strongly convex functions, we prove non-accelerated rates of global convergence of AHB and its weighted version. We conduct several numerical experiments on minimizing quadratic and non-quadratic functions to demonstrate the advantages of using averaging for HB.