Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Xiaoning, Zeng, Shangzhi, Zhang, Jin, Zhang, Lezhi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910209984692224
author Bai, Xiaoning
Zeng, Shangzhi
Zhang, Jin
Zhang, Lezhi
author_facet Bai, Xiaoning
Zeng, Shangzhi
Zhang, Jin
Zhang, Lezhi
contents In this paper, we study a class of bilevel optimization problems where the lower-level problem is a convex composite optimization model, which arises in various applications, including bilevel hyperparameter selection for regularized regression models. To solve these problems, we propose an Alternating Gradient-type algorithm with Inexact Lower-level Solutions (AGILS) based on a Moreau envelope-based reformulation of the bilevel optimization problem. The proposed algorithm does not require exact solutions of the lower-level problem at each iteration, improving computational efficiency. We prove the convergence of AGILS to stationary points and, under the Kurdyka-Łojasiewicz (KL) property, establish its sequential convergence. Numerical experiments, including a toy example and a bilevel hyperparameter selection problem for the sparse group Lasso model, demonstrate the effectiveness of the proposed AGILS.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18929
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
Bai, Xiaoning
Zeng, Shangzhi
Zhang, Jin
Zhang, Lezhi
Optimization and Control
90C26, 90C30, 49M37, 65K05
In this paper, we study a class of bilevel optimization problems where the lower-level problem is a convex composite optimization model, which arises in various applications, including bilevel hyperparameter selection for regularized regression models. To solve these problems, we propose an Alternating Gradient-type algorithm with Inexact Lower-level Solutions (AGILS) based on a Moreau envelope-based reformulation of the bilevel optimization problem. The proposed algorithm does not require exact solutions of the lower-level problem at each iteration, improving computational efficiency. We prove the convergence of AGILS to stationary points and, under the Kurdyka-Łojasiewicz (KL) property, establish its sequential convergence. Numerical experiments, including a toy example and a bilevel hyperparameter selection problem for the sparse group Lasso model, demonstrate the effectiveness of the proposed AGILS.
title Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
topic Optimization and Control
90C26, 90C30, 49M37, 65K05
url https://arxiv.org/abs/2412.18929