Safe Gradient Flow for Bilevel Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharifi, Sina, Abolfazli, Nazanin, Hamedani, Erfan Yazdandoost, Fazlyab, Mahyar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915208899854336
author Sharifi, Sina
Abolfazli, Nazanin
Hamedani, Erfan Yazdandoost
Fazlyab, Mahyar
author_facet Sharifi, Sina
Abolfazli, Nazanin
Hamedani, Erfan Yazdandoost
Fazlyab, Mahyar
contents Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoretic approach to solving bilevel optimization problems. Our method consists of two components: a gradient flow mechanism to minimize the upper-level objective and a safety filter to enforce the constraints imposed by the lower-level problem. Together, these components form a safe gradient flow that solves the bilevel problem in a single loop. To improve scalability with respect to the lower-level problem's dimensions, we introduce a relaxed formulation and design a compact variant of the safe gradient flow. This variant minimizes the upper-level objective while ensuring the lower-level decision variable remains within a user-defined suboptimality. Using Lyapunov analysis, we establish convergence guarantees for the dynamics, proving that they converge to a neighborhood of the optimal solution. Numerical experiments further validate the effectiveness of the proposed approaches. Our contributions provide both theoretical insights and practical tools for efficiently solving bilevel optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16520
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safe Gradient Flow for Bilevel Optimization
Sharifi, Sina
Abolfazli, Nazanin
Hamedani, Erfan Yazdandoost
Fazlyab, Mahyar
Optimization and Control
Machine Learning
Systems and Control
Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoretic approach to solving bilevel optimization problems. Our method consists of two components: a gradient flow mechanism to minimize the upper-level objective and a safety filter to enforce the constraints imposed by the lower-level problem. Together, these components form a safe gradient flow that solves the bilevel problem in a single loop. To improve scalability with respect to the lower-level problem's dimensions, we introduce a relaxed formulation and design a compact variant of the safe gradient flow. This variant minimizes the upper-level objective while ensuring the lower-level decision variable remains within a user-defined suboptimality. Using Lyapunov analysis, we establish convergence guarantees for the dynamics, proving that they converge to a neighborhood of the optimal solution. Numerical experiments further validate the effectiveness of the proposed approaches. Our contributions provide both theoretical insights and practical tools for efficiently solving bilevel optimization problems.
title Safe Gradient Flow for Bilevel Optimization
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2501.16520