Accelerating Diagonal Methods for Bilevel Optimization: Unified Convergence via Continuous-Time Dynamics
Optimization and Control
2025-05-21 v1
Abstract
We analyze fast diagonal methods for simple bilevel programs. Guided by the analysis of the corresponding continuous-time dynamics, we provide a unified convergence analysis under general geometric conditions, including H\"olderian growth and the Attouch-Czarnecki condition. Our results yield explicit convergence rates and guarantee weak convergence to a solution of the bilevel problem. In particular, we improve and extend recent results on accelerated schemes, offering novel insights into the trade-offs between geometry, regularization decay, and algorithmic design. Numerical experiments illustrate the advantages of more flexible methods and support our theoretical findings.
Cite
@article{arxiv.2505.14389,
title = {Accelerating Diagonal Methods for Bilevel Optimization: Unified Convergence via Continuous-Time Dynamics},
author = {Radu Ioan Boţ and Enis Chenchene and Ernö Robert Csetnek and David Alexander Hulett},
journal= {arXiv preprint arXiv:2505.14389},
year = {2025}
}