An Adaptive Linesearch-free Method for Monotone Variational Inequalities under Local Lipschitz Continuity
Abstract
The forward-reflected-backward (FRB) splitting solves inclusion problems involving the sum of a maximally monotone operator and a monotone Lipschitz continuous operator. Each iteration performs one resolvent step and one evaluation of the Lipschitz operator, plus a reflection term with coefficient one that reuses the previous operator value. We consider the setting where the maximally monotone operator is the subdifferential of a proper, lower semicontinuous, convex function. We identify the tight admissible range of constant reflection coefficients, namely all values larger than one half for a sufficiently small stepsize. We then propose a linesearch-free adaptive variant of FRB for locally Lipschitz continuous operators, in which both the stepsize and the reflection coefficient change across iterations. The stepsize is computed in closed form from a simple local Lipschitz estimate, without requiring the existence or knowledge of a global Lipschitz constant, while maintaining the iteration cost of FRB. The analysis of both methods relies on a new Lyapunov function that combines the distance to a solution, successive differences of iterates, and a gap-type term. The individual terms need not decrease along the iterates, but the stepsize conditions ensure that their weighted combination does. Moreover, alongside nonasymptotic rates, we derive explicit lower bounds on the generated stepsizes, and showcase the effectiveness of the adaptive method through numerical experiments on minimax problems, equilibrium models, and regularized regression.
Related
- Extragradient and Past Extragradient Methods for (L0,L1)-Lipschitz Variational Inequalities
- An Inertial Self-Adaptive Tseng Method for Non-Lipschitz Monotone Variational Inclusions on Hadamard Manifolds
- Primal-dual forward-reflected splitting with linesearch for distributed min-max problems under local Lipschitz smoothness
- GRAAL for variational inequalities revisited: sharp parameter range and adaptive step sizes
- Parameter-Free Adaptive Extragradient Methods for Generalized-Smooth Variational Inequalities
BibTeX
@misc{ou2026adaptive,
title = {{An Adaptive Linesearch-free Method for Monotone Variational Inequalities under Local Lipschitz Continuity}},
author = {Hongjia Ou and Andreas Themelis and Puya Latafat},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15936},
eprint = {2609.15936},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15936},
}
RIS
TY - UNPB
TI - An Adaptive Linesearch-free Method for Monotone Variational Inequalities under Local Lipschitz Continuity
AU - Hongjia Ou
AU - Andreas Themelis
AU - Puya Latafat
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15936
UR - https://arxiv.org/abs/2609.15936
AB - The forward-reflected-backward (FRB) splitting solves inclusion problems involving the sum of a maximally monotone operator and a monotone Lipschitz continuous operator. Each iteration performs one resolvent step and one evaluation of the Lipschitz operator, plus a reflection term with coefficient one that reuses the previous operator value. We consider the setting where the maximally monotone operator is the subdifferential of a proper, lower semicontinuous, convex function. We identify the tight admissible range of constant reflection coefficients, namely all values larger than one half for a sufficiently small stepsize. We then propose a linesearch-free adaptive variant of FRB for locally Lipschitz continuous operators, in which both the stepsize and the reflection coefficient change across iterations. The stepsize is computed in closed form from a simple local Lipschitz estimate, without requiring the existence or knowledge of a global Lipschitz constant, while maintaining the iteration cost of FRB. The analysis of both methods relies on a new Lyapunov function that combines the distance to a solution, successive differences of iterates, and a gap-type term. The individual terms need not decrease along the iterates, but the stepsize conditions ensure that their weighted combination does. Moreover, alongside nonasymptotic rates, we derive explicit lower bounds on the generated stepsizes, and showcase the effectiveness of the adaptive method through numerical experiments on minimax problems, equilibrium models, and regularized regression.
ER -