arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.02459math.OC
收藏

凸优化中基于拉格朗日的方法:具有非遍历收敛率的预测-校正框架

Lagrangian-based methods in convex optimization: prediction-correction frameworks with non-ergodic convergence rates

Tao Zhang, Yong Xia, Shiru Li

AI总结:

本文针对等式约束凸优化问题,提出了基于拉格朗日方法的预测-校正框架,通过更新乘子策略设计算法,并证明了其在一般凸和强凸条件下的非遍历收敛率,同时应用于ADMM类方法。

摘要:

基于拉格朗日的方法是求解等式约束凸优化问题的经典方法。我们为此类方法及其变体提出了新颖的预测-校正框架,该框架在一般凸优化下可实现$O(1/k)$的非遍历收敛率,在目标函数强凸或梯度 Lipschitz 连续的假设下可实现$O(1/k^2)$的非遍历收敛率。我们给出了两种方法(更新乘子一次或两次)来设计满足所提出预测-校正框架的算法。作为应用,我们为一些著名的基于拉格朗日的方法(特别是 ADMM 类型方法和多块 ADMM 类型方法)建立了非遍历收敛率。

英文摘要:

Lagrangian-based methods are classical methods for solving convex optimization problems with equality constraints. We present novel prediction-correction frameworks for such methods and their variants, which can achieve $O(1/k)$ non-ergodic convergence rates for general convex optimization and $O(1/k^2)$ non-ergodic convergence rates under the assumption that the objective function is strongly convex or gradient Lipschitz continuous. We give two approaches ($updating~multiplier~once$ $or~twice$) to design algorithms satisfying the presented prediction-correction frameworks. As applications, we establish non-ergodic convergence rates for some well-known Lagrangian-based methods (esp., the ADMM type methods and the multi-block ADMM type methods).

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。

↑