Guardado en:
Detalles Bibliográficos
Autores principales: Bohne, Jason, Petrulionyte, Ieva, Arbel, Michael, Mairal, Julien, Polak, Paweł
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.15363
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908780553306112
author Bohne, Jason
Petrulionyte, Ieva
Arbel, Michael
Mairal, Julien
Polak, Paweł
author_facet Bohne, Jason
Petrulionyte, Ieva
Arbel, Michael
Mairal, Julien
Polak, Paweł
contents Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and perform suboptimally in online, non-stationary scenarios. We propose SmoothFBO, the first algorithm for non-stationary FBO with both theoretical guarantees and practical scalability. SmoothFBO introduces a time-smoothed stochastic hypergradient estimator that reduces variance through a window parameter, enabling stable outer-loop updates with sublinear regret. Importantly, the classical parametric bilevel case is a special reduction of our framework, making SmoothFBO a natural extension to online, non-stationary settings. Empirically, SmoothFBO consistently outperforms existing FBO methods in non-stationary hyperparameter optimization and model-based reinforcement learning, demonstrating its practical effectiveness. Together, these results establish SmoothFBO as a general, theoretically grounded, and practically viable foundation for bilevel optimization in online, non-stationary scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15363
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Non-Stationary Functional Bilevel Optimization
Bohne, Jason
Petrulionyte, Ieva
Arbel, Michael
Mairal, Julien
Polak, Paweł
Machine Learning
Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and perform suboptimally in online, non-stationary scenarios. We propose SmoothFBO, the first algorithm for non-stationary FBO with both theoretical guarantees and practical scalability. SmoothFBO introduces a time-smoothed stochastic hypergradient estimator that reduces variance through a window parameter, enabling stable outer-loop updates with sublinear regret. Importantly, the classical parametric bilevel case is a special reduction of our framework, making SmoothFBO a natural extension to online, non-stationary settings. Empirically, SmoothFBO consistently outperforms existing FBO methods in non-stationary hyperparameter optimization and model-based reinforcement learning, demonstrating its practical effectiveness. Together, these results establish SmoothFBO as a general, theoretically grounded, and practically viable foundation for bilevel optimization in online, non-stationary scenarios.
title Non-Stationary Functional Bilevel Optimization
topic Machine Learning
url https://arxiv.org/abs/2601.15363