arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1408.3595math.OCcs.NAcs.SYeess.SYmath.NA
收藏

基于积分二次约束的优化算法分析与设计

Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints

Laurent Lessard, Benjamin Recht, Andrew Packard

AI总结:

本文提出了一种利用积分二次约束(IQC)理论分析和设计迭代优化算法的新框架,通过证明关于凸函数的新不等式,为优化算法提供了新的分析工具,并通过求解小规模半正定规划问题,得出了梯度法、重力球法、Nesterov加速法等算法的收敛率上界。

摘要:

本文提出了一种新的框架,用于分析和设计基于鲁棒控制理论中积分二次约束(IQC)概念的迭代优化算法。IQC提供了复杂互联系统的稳定性充分条件,这些条件可以通过半正定规划进行检验。我们讨论了如何将IQC理论应用于优化算法的研究,证明了关于凸函数的新不等式,并提供了一种适用于优化研究者的IQC理论变体。利用这些不等式,我们通过求解小规模、简单的半正定规划问题,推导出了梯度法、重力球法、Nesterov加速法及相关变种的数值收敛率上界。我们还简要展示了这些技术如何用于寻找具有期望性能特征的优化算法,从而建立了一种新的算法设计方法。

英文摘要:

This manuscript develops a new framework to analyze and design iterative optimization algorithms built on the notion of Integral Quadratic Constraints (IQC) from robust control theory. IQCs provide sufficient conditions for the stability of complicated interconnected systems, and these conditions can be checked by semidefinite programming. We discuss how to adapt IQC theory to study optimization algorithms, proving new inequalities about convex functions and providing a version of IQC theory adapted for use by optimization researchers. Using these inequalities, we derive numerical upper bounds on convergence rates for the gradient method, the heavy-ball method, Nesterov's accelerated method, and related variants by solving small, simple semidefinite programming problems. We also briefly show how these techniques can be used to search for optimization algorithms with desired performance characteristics, establishing a new methodology for algorithm design.

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。

↑