Convergence of difference inclusions via a diameter criterion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Lexiao, Song, Mingzhi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914565316411392
author Lai, Lexiao
Song, Mingzhi
author_facet Lai, Lexiao
Song, Mingzhi
contents We study discrete dynamics governed by a difference inclusion whose increment is the sum of a selection from a set-valued map and a noise term. For any bounded realization, convergence follows once the inter-iterate diameter is controlled by the variation of a continuous potential. The limit point is then critical for a scaled outer limit of the update map. To certify this diameter criterion, we develop a stratified descent framework: we project iterates onto a suitable stratification and track a potential that decreases up to a summable error. Combining the diameter criterion with a diameter estimate obtained from this framework yields convergence of common first-order optimization methods under step sizes of order $1/k$. The guarantees cover inexact and stochastic subgradient methods, as well as the momentum method, for locally Lipschitz objectives definable in polynomially bounded o-minimal structures. Our arguments are entirely discrete, with no appeal to continuous-time approximations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14345
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Convergence of difference inclusions via a diameter criterion
Lai, Lexiao
Song, Mingzhi
Optimization and Control
65K10, 39A05, 03C64
We study discrete dynamics governed by a difference inclusion whose increment is the sum of a selection from a set-valued map and a noise term. For any bounded realization, convergence follows once the inter-iterate diameter is controlled by the variation of a continuous potential. The limit point is then critical for a scaled outer limit of the update map. To certify this diameter criterion, we develop a stratified descent framework: we project iterates onto a suitable stratification and track a potential that decreases up to a summable error. Combining the diameter criterion with a diameter estimate obtained from this framework yields convergence of common first-order optimization methods under step sizes of order $1/k$. The guarantees cover inexact and stochastic subgradient methods, as well as the momentum method, for locally Lipschitz objectives definable in polynomially bounded o-minimal structures. Our arguments are entirely discrete, with no appeal to continuous-time approximations.
title Convergence of difference inclusions via a diameter criterion
topic Optimization and Control
65K10, 39A05, 03C64
url https://arxiv.org/abs/2605.14345