paper-with-me

Papers

Non-Stationary Functional Bilevel Optimization

2026-01-21 · Jason Bohne, Ieva Petrulionyte, Michael Arbel, Julien Mairal, Paweł Polak arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.15363

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter OptimizationReinforcement LearningBilevel Optimization

Similar Papers 제목 키워드 기반

Accelerating Inexact HyperGradient Descent for Bilevel Optimization

2023-06-30 · Haikuo Yang, Luo Luo, Chris Junchi Li, Michael I. Jordan

We present a method for solving general nonconvex-strongly-convex bilevel optimization problems. Our method -- the \emph{Restarted Accelerated HyperGradient Descent} (\texttt{RAHGD}) method -- finds an $\epsilon$-first-o…

Bilevel Optimization

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

2023-09-21 · NeurIPS 2023 11

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown …

A Generalized Alternating Method for Bilevel Learning under the Polyak-Łojasiewicz Condition

2023-06-04 · Quan Xiao, Songtao Lu, Tianyi Chen

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown …

Bilevel OptimizationHyperparameter OptimizationMeta-Learning

Adaptive Mirror Descent Bilevel Optimization

2023-11-08 · Feihu Huang

In the paper, we propose a class of efficient adaptive bilevel methods based on mirror descent for nonconvex bilevel optimization, where its upper-level problem is nonconvex possibly with nonsmooth regularization, and it…

Bilevel Optimization

Functional Bilevel Optimization for Machine Learning

2024-03-29 · Ieva Petrulionyte, Julien Mairal, Michael Arbel

In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solve…

Bilevel OptimizationPrediction