arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02494cs.LG
收藏

用于可微优化的全一阶层

A Fully First-Order Layer for Differentiable Optimization

University of California, Berkeley(加州大学伯克利分校);DeepMind(深度思维)

Zihao Zhao, Kai-Chia Mo, Shing-Hei Ho, Brandon Amos, Kai Wang

AI总结:

提出一种仅使用一阶信息计算梯度的算法,通过将可微优化重写为双层优化并引入活动集拉格朗日超梯度方法,避免Hessian计算,实现高效近似。

摘要:

可微优化层使得学习系统能够通过求解嵌入的优化问题来做出决策。然而,通过隐式微分计算梯度需要求解一个包含Hessian项的线性系统,这既计算密集又内存密集。为了解决这一挑战,我们提出了一种仅使用一阶信息计算梯度的新算法。关键洞察是将可微优化重写为双层优化问题,并利用双层方法的最新进展。具体来说,我们引入了一个活动集拉格朗日超梯度方法,避免了Hessian计算,并提供了有限时间、非渐近的近似保证。我们证明,仅使用一阶信息即可在$\tilde{O}(1)$时间内计算出近似超梯度,从而使得约束双层优化的总体复杂度为$\tilde{O}(\delta^{-1}\epsilon^{-3})$,这与非光滑非凸优化的最佳已知速率相匹配。此外,我们发布了一个开源Python库,可以轻松地从现有求解器进行适配。源代码可在该https URL获取。

英文摘要:

Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is both compute- and memory-intensive. To address this challenge, we propose a novel algorithm that computes the gradient using only first-order information. The key insight is to rewrite the differentiable optimization as a bilevel optimization problem and leverage recent advances in bilevel methods. Specifically, we introduce an active-set Lagrangian hypergradient oracle that avoids Hessian evaluations and provides finite-time, non-asymptotic approximation guarantees. We show that an approximate hypergradient can be computed using only first-order information in $\tilde{O}(1)$ time, leading to an overall complexity of $\tilde{O}(δ^{-1}ε^{-3})$ for constrained bilevel optimization, which matches the best known rate for non-smooth non-convex optimization. Furthermore, we release an open-source Python library that can be easily adapted from existing solvers. The source code is available at https://github.com/guaguakai/FFOLayer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑