Adaptive Algorithms for Nonconvex Bilevel Optimization under PŁ Conditions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Xu, Du, Yinglin, Xiao, Rufeng, Jiang, Rujun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911347143344128
author Shi, Xu
Du, Yinglin
Xiao, Rufeng
Jiang, Rujun
author_facet Shi, Xu
Du, Yinglin
Xiao, Rufeng
Jiang, Rujun
contents Existing methods for nonconvex bilevel optimization (NBO) require prior knowledge of first- and second-order problem-specific parameters (e.g., Lipschitz constants and the Polyak-Łojasiewicz (PŁ) parameters) to set step sizes, a requirement that poses practical limitations when such parameters are unknown or computationally expensive. We introduce the Adaptive Fully First-order Bilevel Approximation (AF${}^2$BA) algorithm and its accelerated variant, A${}^2$F${}^2$BA, for solving NBO problems under the PŁ conditions. To our knowledge, these are the first methods to employ fully adaptive step size strategies, eliminating the need for any problem-specific parameters in NBO. We prove that both algorithms achieve $\mathcal{O}(1/ε^2)$ iteration complexity for finding an $ε$-stationary point, matching the iteration complexity of existing well-tuned methods. Furthermore, we show that A${}^2$F${}^2$BA enjoys a near-optimal first-order oracle complexity of $\tilde{\mathcal{O}}(1/ε^2)$, matching the oracle complexity of existing well-tuned methods, and aligning with the complexity of gradient descent for smooth nonconvex single-level optimization when ignoring the logarithmic factors.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Algorithms for Nonconvex Bilevel Optimization under PŁ Conditions
Shi, Xu
Du, Yinglin
Xiao, Rufeng
Jiang, Rujun
Optimization and Control
Existing methods for nonconvex bilevel optimization (NBO) require prior knowledge of first- and second-order problem-specific parameters (e.g., Lipschitz constants and the Polyak-Łojasiewicz (PŁ) parameters) to set step sizes, a requirement that poses practical limitations when such parameters are unknown or computationally expensive. We introduce the Adaptive Fully First-order Bilevel Approximation (AF${}^2$BA) algorithm and its accelerated variant, A${}^2$F${}^2$BA, for solving NBO problems under the PŁ conditions. To our knowledge, these are the first methods to employ fully adaptive step size strategies, eliminating the need for any problem-specific parameters in NBO. We prove that both algorithms achieve $\mathcal{O}(1/ε^2)$ iteration complexity for finding an $ε$-stationary point, matching the iteration complexity of existing well-tuned methods. Furthermore, we show that A${}^2$F${}^2$BA enjoys a near-optimal first-order oracle complexity of $\tilde{\mathcal{O}}(1/ε^2)$, matching the oracle complexity of existing well-tuned methods, and aligning with the complexity of gradient descent for smooth nonconvex single-level optimization when ignoring the logarithmic factors.
title Adaptive Algorithms for Nonconvex Bilevel Optimization under PŁ Conditions
topic Optimization and Control
url https://arxiv.org/abs/2512.24291