Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Wei, Yu, Chengming, Zeng, Shangzhi, Zhang, Jin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913213899079680
author Yao, Wei
Yu, Chengming
Zeng, Shangzhi
Zhang, Jin
author_facet Yao, Wei
Yu, Chengming
Zeng, Shangzhi
Zhang, Jin
contents This paper presents a new approach and algorithm for solving a class of constrained Bi-Level Optimization (BLO) problems in which the lower-level problem involves constraints coupling both upper-level and lower-level variables. Such problems have recently gained significant attention due to their broad applicability in machine learning. However, conventional gradient-based methods unavoidably rely on computationally intensive calculations related to the Hessian matrix. To address this challenge, we begin by devising a smooth proximal Lagrangian value function to handle the constrained lower-level problem. Utilizing this construct, we introduce a single-level reformulation for constrained BLOs that transforms the original BLO problem into an equivalent optimization problem with smooth constraints. Enabled by this reformulation, we develop a Hessian-free gradient-based algorithm-termed proximal Lagrangian Value function-based Hessian-free Bi-level Algorithm (LV-HBA)-that is straightforward to implement in a single loop manner. Consequently, LV-HBA is especially well-suited for machine learning applications. Furthermore, we offer non-asymptotic convergence analysis for LV-HBA, eliminating the need for traditional strong convexity assumptions for the lower-level problem while also being capable of accommodating non-singleton scenarios. Empirical results substantiate the algorithm's superior practical performance.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm
Yao, Wei
Yu, Chengming
Zeng, Shangzhi
Zhang, Jin
Machine Learning
Optimization and Control
This paper presents a new approach and algorithm for solving a class of constrained Bi-Level Optimization (BLO) problems in which the lower-level problem involves constraints coupling both upper-level and lower-level variables. Such problems have recently gained significant attention due to their broad applicability in machine learning. However, conventional gradient-based methods unavoidably rely on computationally intensive calculations related to the Hessian matrix. To address this challenge, we begin by devising a smooth proximal Lagrangian value function to handle the constrained lower-level problem. Utilizing this construct, we introduce a single-level reformulation for constrained BLOs that transforms the original BLO problem into an equivalent optimization problem with smooth constraints. Enabled by this reformulation, we develop a Hessian-free gradient-based algorithm-termed proximal Lagrangian Value function-based Hessian-free Bi-level Algorithm (LV-HBA)-that is straightforward to implement in a single loop manner. Consequently, LV-HBA is especially well-suited for machine learning applications. Furthermore, we offer non-asymptotic convergence analysis for LV-HBA, eliminating the need for traditional strong convexity assumptions for the lower-level problem while also being capable of accommodating non-singleton scenarios. Empirical results substantiate the algorithm's superior practical performance.
title Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2401.16164