arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02015math.OC
收藏

用于复合非凸非光滑优化的统一不精确随机ADMM

A Unified Inexact Stochastic ADMM for Composite Nonconvex and Nonsmooth Optimization

Yuxuan Zeng, Jianchao Bai, Shengjia Wang, Zhiguo Wang

AI总结:

提出统一的不精确随机ADMM框架以求解复合非凸非光滑优化,涵盖多种现有算法并设计新的加速混合随机ADMM,证明其次线性与线性收敛,实验验证了有效性。

摘要:

本文提出了一个不精确随机交替方向乘子法(ADMM)的统一框架,用于求解受线性约束的非凸问题,其目标函数由有限和光滑函数的平均与一个非光滑但可能非凸的函数组成。新框架具有很强的通用性。首先,它不仅涵盖了SADMM、SVRG-ADMM和SPIDER-ADMM等若干现有算法,还指导我们设计了一种新颖的加速混合随机ADMM算法,该算法利用一种新的混合估计量来权衡方差与偏差。其次,它使我们能够在收敛性分析中采用更灵活的对偶步长。在一些温和条件下,我们的统一框架保持了$\mathcal{O}(1/T)$的次线性收敛。此外,我们在误差界条件下建立了线性收敛。最后,数值实验证明了新算法在一些非光滑、非凸问题上的有效性。

英文摘要:

In this paper, we propose a unified framework of inexact stochastic Alternating Direction Method of Multipliers (ADMM) for solving nonconvex problems subject to linear constraints, whose objective comprises an average of finite-sum smooth functions and a nonsmooth but possibly nonconvex function. The new framework is highly versatile. Firstly, it not only covers several existing algorithms such as SADMM, SVRG-ADMM, and SPIDER-ADMM but also guides us to design a novel accelerated hybrid stochastic ADMM algorithm, which utilizes a new hybrid estimator to trade-off variance and bias. Second, it enables us to exploit a more flexible dual stepsize in the convergence analysis. Under some mild conditions, our unified framework preserves $\mathcal{O}(1/T)$ sublinear convergence. Additionally, we establish the linear convergence under error bound conditions. Finally, numerical experiments demonstrate the efficacy of the new algorithm for some nonsmooth and nonconvex problems.

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。

↑