Global stability of first-order methods for coercive tame functions

2023/08/02 by Josz, Cédric, Lai, Lexiao · 2 citations
#FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2308.00899

Abstract

We consider first-order methods with constant step size for minimizing locally Lipschitz coercive functions that are tame in an o-minimal structure on the real field. We prove that if the method is approximated by subgradient trajectories, then the iterates eventually remain in a neighborhood of a connected component of the set of critical points. Under suitable method-dependent regularity assumptions, this result applies to the subgradient method with momentum, the stochastic subgradient method with random reshuffling and momentum, and the random-permutations cyclic coordinate descent method.

Cited by

• Lyapunov stability of the Euler method
• On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem

Related

• Stability of first-order methods in tame optimization
• Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
• Sufficient conditions for instability of the subgradient method with constant step size
• Stochastic subgradient method converges on tame functions
• Active manifolds, stratifications, and convergence to local minima in nonsmooth optimization