cs.LG, cs.SY, eess.SY, math.OC

Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima

arXiv:2307.07030v3 Announce Type: replace-cross
Abstract: This paper considers the problem of understanding the behavior of a general class of accelerated gradient methods on smooth nonconvex functions. Motivated by some recent works that have propose…