arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.09407math.OCcs.AI
收藏

使用单调算子理论的三层与多层优化

Trilevel and Multilevel Optimization using Monotone Operator Theory

Czech Technical University(捷克技术大学)

Allahkaram Shafiei, Vyacheslav Kungurtsev, Jakub Marecek

AI总结:

本文研究嵌套凸优化约束下的多层优化问题,基于不动点理论提出一种一阶算法,并分析了其在不同参数机制下的收敛性及收敛速率。

摘要:

我们考虑一类相当一般的多层优化问题,其中需要在嵌套凸优化问题的最优性约束下最小化一个凸目标函数。作为特例,我们考虑一个三层优化问题,其中两个较低层的目标函数由一个光滑项和一个非光滑项之和组成。基于不动点理论及相关论证,我们提出了一种自然的一阶算法,并在几种参数机制下分析了其收敛性及收敛速率。

英文摘要:

We consider rather a general class of multi-level optimization problems, where a convex objective function is to be minimized subject to constraints of optimality of nested convex optimization problems. As a special case, we consider a trilevel optimization problem, where the objective of the two lower layers consists of a sum of a smooth and a non-smooth term.~Based on fixed-point theory and related arguments, we present a natural first-order algorithm and analyze its convergence and rates of convergence in several regimes of parameters.

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。

↑