arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.03086math.OCcs.LG
收藏

锥优化的对偶拉格朗日学习

Dual Lagrangian Learning for Conic Optimization

H. Milton Steward School of Industrial and Systems Engineering(H. Milton Stewart工业与系统工程学院);Georgia Institute of Technology(佐治亚理工学院)

Mathieu Tanneau, Pascal Van Hentenryck

AI总结:

本文提出对偶拉格朗日学习(DLL),利用锥对偶性和机器学习模型为线性和非线性锥优化问题生成对偶可行解,提供有效的拉格朗日对偶界,显著优于现有学习方法,并比商业求解器快1000倍,平均最优性差距低于0.5%。

摘要:

本文提出了对偶拉格朗日学习(DLL),一种用于对偶锥优化代理的有原则的学习方法。DLL利用锥对偶性和机器学习模型的表示能力,为线性和非线性锥优化问题提供高对偶性、对偶可行的解,从而得到有效的拉格朗日对偶界。本文介绍了一种系统的对偶补全程序、可微的锥投影层,以及基于拉格朗日对偶性的自监督学习框架。它还提供了广泛类别的锥问题的闭式对偶补全公式,消除了对昂贵隐式层的需求。DLL的有效性在线性和非线性锥优化问题上得到了验证。所提出的方法显著优于最先进的基于学习的方法,并且相对于商业内点求解器实现了1000倍的加速,平均最优性差距低于0.5%。

英文摘要:

This paper presents Dual Lagrangian Learning (DLL), a principled learning methodology for dual conic optimization proxies. DLL leverages conic duality and the representation power of ML models to provide high-duality, dual-feasible solutions, and therefore valid Lagrangian dual bounds, for linear and nonlinear conic optimization problems. The paper introduces a systematic dual completion procedure, differentiable conic projection layers, and a self-supervised learning framework based on Lagrangian duality. It also provides closed-form dual completion formulae for broad classes of conic problems, which eliminate the need for costly implicit layers. The effectiveness of DLL is demonstrated on linear and nonlinear conic optimization problems. The proposed methodology significantly outperforms a state-of-the-art learning-based method, and achieves 1000x speedups over commercial interior-point solvers with optimality gaps under 0.5\% on average.

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。

↑