Asymptotic Analysis of Gradient Mapping-type Stationarity Measure for the Sum of Nonconvex Nonsmooth Functions and Applications to Proximal Gradient-type Algorithms
Abstract
We propose a gradient mapping-type stationarity measure for the sum of two possibly nonsmooth nonconvex functions. Under suitable regularity assumptions, we show that Fréchet or proximal stationarity can be characterized through asymptotic vanishing of the proposed measure along some convergent sequence. We also establish analogous asymptotic results for a smoothing-based variant of the measure, which enables us to combine the proposed framework with smoothing techniques developed for nonsmooth optimization. As an application of our analysis of the stationarity measure, we provide an affirmative answer to an open question raised by [Olikier-Waldspurger, SIAM J. Optim., 2025] on whether every cluster point of a sequence generated by a proximal gradient method is a proximal stationary point under local Lipschitz smoothness of one component of the cost function. As a second application, we propose a proximal variable smoothing algorithm with a nonmonotone linesearch for minimizing the sum of two nonsmooth nonconvex functions under lower regularity of one component and prox-regularity of the other. For the proposed algorithm, we show that every cluster point of a subsequence such that the stationarity measure vanishes is a Fréchet stationary point.
Related
- Deterministic Oracle Complexity for Goldstein Stationarity in Nonsmooth Nonconvex Optimization with Constraints
- Variable Bregman Majorization-Minimization algorithms for nonconvex nonsmooth optimization, with application to Poisson imaging
- Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints
- A Proximal Gradient Method for Nonconvex Nonsmooth Optimization with Applications
- Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization
BibTeX
@misc{kume2026asymptotic,
title = {{Asymptotic Analysis of Gradient Mapping-type Stationarity Measure for the Sum of Nonconvex Nonsmooth Functions and Applications to Proximal Gradient-type Algorithms}},
author = {Keita Kume and Isao Yamada},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.03950},
eprint = {2609.03950},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03950},
}
RIS
TY - UNPB
TI - Asymptotic Analysis of Gradient Mapping-type Stationarity Measure for the Sum of Nonconvex Nonsmooth Functions and Applications to Proximal Gradient-type Algorithms
AU - Keita Kume
AU - Isao Yamada
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2609.03950
UR - https://arxiv.org/abs/2609.03950
AB - We propose a gradient mapping-type stationarity measure for the sum of two possibly nonsmooth nonconvex functions. Under suitable regularity assumptions, we show that Fréchet or proximal stationarity can be characterized through asymptotic vanishing of the proposed measure along some convergent sequence. We also establish analogous asymptotic results for a smoothing-based variant of the measure, which enables us to combine the proposed framework with smoothing techniques developed for nonsmooth optimization. As an application of our analysis of the stationarity measure, we provide an affirmative answer to an open question raised by [Olikier-Waldspurger, SIAM J. Optim., 2025] on whether every cluster point of a sequence generated by a proximal gradient method is a proximal stationary point under local Lipschitz smoothness of one component of the cost function. As a second application, we propose a proximal variable smoothing algorithm with a nonmonotone linesearch for minimizing the sum of two nonsmooth nonconvex functions under lower regularity of one component and prox-regularity of the other. For the proposed algorithm, we show that every cluster point of a subsequence such that the stationarity measure vanishes is a Fréchet stationary point.
ER -