arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.00565math.OCcs.SYeess.SY
收藏

基于积分二次约束的优化算法综合:教程

Optimization Algorithm Synthesis based on Integral Quadratic Constraints: A Tutorial

Carsten W. Scherer, Christian Ebenbauer, Tobias Holicki

AI总结:

本教程介绍基于动态积分二次约束的优化算法综合机制,通过求解小规模凸半定规划设计具有最优保证收敛率的加速梯度下降算法,并扩展至极值控制器设计,数值实验验证了方法的有效性。

摘要:

我们以教程方式揭示基于动态积分二次约束的优化算法综合机制。我们展示了这些来自鲁棒控制的工具如何通过求解小规模凸半定规划,设计出具有最优保证收敛率的加速梯度下降算法。结果表明,这可扩展至极值控制器的设计,旨在将一般线性闭环系统的输出调节至目标函数的最小值。数值实验表明,我们不仅能恢复梯度下降和Nesterov加速一阶算法的三动量变体,还能在梯度信息通过非平凡动态(如时滞)传递时自动综合出最优算法。

英文摘要:

We expose in a tutorial fashion the mechanisms which underlie the synthesis of optimization algorithms based on dynamic integral quadratic constraints. We reveal how these tools from robust control allow to design accelerated gradient descent algorithms with optimal guaranteed convergence rates by solving small-sized convex semi-definite programs. It is shown that this extends to the design of extremum controllers, with the goal to regulate the output of a general linear closed-loop system to the minimum of an objective function. Numerical experiments illustrate that we can not only recover gradient decent and the triple momentum variant of Nesterov's accelerated first order algorithm, but also automatically synthesize optimal algorithms even if the gradient information is passed through non-trivial dynamics, such as time-delays.

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。

↑