Learning Theory for Kernel Bilevel Optimization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Khoury, Fares El, Pauwels, Edouard, Vaiter, Samuel, Arbel, Michael
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911267208298496
author Khoury, Fares El
Pauwels, Edouard
Vaiter, Samuel
Arbel, Michael
author_facet Khoury, Fares El
Pauwels, Edouard
Vaiter, Samuel
Arbel, Michael
contents Bilevel optimization has emerged as a technique for addressing a wide range of machine learning problems that involve an outer objective implicitly determined by the minimizer of an inner problem. While prior works have primarily focused on the parametric setting, a learning-theoretic foundation for bilevel optimization in the nonparametric case remains relatively unexplored. In this paper, we take a first step toward bridging this gap by studying Kernel Bilevel Optimization (KBO), where the inner objective is optimized over a reproducing kernel Hilbert space. This setting enables rich function approximation while providing a foundation for rigorous theoretical analysis. In this context, we derive novel finite-sample generalization bounds for KBO, leveraging tools from empirical process theory. These bounds further allow us to assess the statistical accuracy of gradient-based methods applied to the empirical discretization of KBO. We numerically illustrate our theoretical findings on a synthetic instrumental variable regression task.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Theory for Kernel Bilevel Optimization
Khoury, Fares El
Pauwels, Edouard
Vaiter, Samuel
Arbel, Michael
Machine Learning
Bilevel optimization has emerged as a technique for addressing a wide range of machine learning problems that involve an outer objective implicitly determined by the minimizer of an inner problem. While prior works have primarily focused on the parametric setting, a learning-theoretic foundation for bilevel optimization in the nonparametric case remains relatively unexplored. In this paper, we take a first step toward bridging this gap by studying Kernel Bilevel Optimization (KBO), where the inner objective is optimized over a reproducing kernel Hilbert space. This setting enables rich function approximation while providing a foundation for rigorous theoretical analysis. In this context, we derive novel finite-sample generalization bounds for KBO, leveraging tools from empirical process theory. These bounds further allow us to assess the statistical accuracy of gradient-based methods applied to the empirical discretization of KBO. We numerically illustrate our theoretical findings on a synthetic instrumental variable regression task.
title Learning Theory for Kernel Bilevel Optimization
topic Machine Learning
url https://arxiv.org/abs/2502.08457