LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Yan, Gao, Bin, Yuan, Ya-xiang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909512082915328
author Yang, Yan
Gao, Bin
Yuan, Ya-xiang
author_facet Yang, Yan
Gao, Bin
Yuan, Ya-xiang
contents Bilevel optimization, with broad applications in machine learning, has an intricate hierarchical structure. Gradient-based methods have emerged as a common approach to large-scale bilevel problems. However, the computation of the hyper-gradient, which involves a Hessian inverse vector product, confines the efficiency and is regarded as a bottleneck. To circumvent the inverse, we construct a sequence of low-dimensional approximate Krylov subspaces with the aid of the Lanczos process. As a result, the constructed subspace is able to dynamically and incrementally approximate the Hessian inverse vector product with less effort and thus leads to a favorable estimate of the hyper-gradient. Moreover, we propose a provable subspace-based framework for bilevel problems where one central step is to solve a small-size tridiagonal linear system. To the best of our knowledge, this is the first time that subspace techniques are incorporated into bilevel optimization. This successful trial not only enjoys $\mathcal{O}(ε^{-1})$ convergence rate but also demonstrates efficiency in a synthetic problem and two deep learning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace
Yang, Yan
Gao, Bin
Yuan, Ya-xiang
Optimization and Control
Machine Learning
Bilevel optimization, with broad applications in machine learning, has an intricate hierarchical structure. Gradient-based methods have emerged as a common approach to large-scale bilevel problems. However, the computation of the hyper-gradient, which involves a Hessian inverse vector product, confines the efficiency and is regarded as a bottleneck. To circumvent the inverse, we construct a sequence of low-dimensional approximate Krylov subspaces with the aid of the Lanczos process. As a result, the constructed subspace is able to dynamically and incrementally approximate the Hessian inverse vector product with less effort and thus leads to a favorable estimate of the hyper-gradient. Moreover, we propose a provable subspace-based framework for bilevel problems where one central step is to solve a small-size tridiagonal linear system. To the best of our knowledge, this is the first time that subspace techniques are incorporated into bilevel optimization. This successful trial not only enjoys $\mathcal{O}(ε^{-1})$ convergence rate but also demonstrates efficiency in a synthetic problem and two deep learning tasks.
title LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2404.03331