Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach

Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
复制标题

鲁棒性和结构利用优化算法:积分二次约束方法

DOI:
--
复制
发表时间:
2019
影响因子:
2.1
通讯作者:
C. Ebenbauer
C. Ebenbauer
中科院分区:
计算机科学4区
文献类型:
--
作者:
Simon Michalowsky;C. Scherer;C. Ebenbauer

文献摘要

参考文献

被引文献

相似文献

我们考虑针对一类具有Lipschitz连续梯度的强凸目标函数的无约束优化问题分析和设计基于梯度的离散时间优化算法的问题。通过制定一个鲁棒性分析问题,并利用适当的适应积分二次约束理论的问题,我们建立了一个框架,允许分析现有算法的收敛速度和鲁棒性,并使设计新的鲁棒优化算法与预先指定的保证能够利用额外的结构在目标函数。
We consider the problem of analysing and designing gradient-based discrete-time optimisation algorithms for a class of unconstrained optimisation problems having strongly convex objective functions with Lipschitz continuous gradient. By formulating the problem as a robustness analysis problem and making use of a suitable adaptation of the theory of integral quadratic constraints, we establish a framework that allows to analyse convergence rates and robustness properties of existing algorithms and enables the design of novel robust optimisation algorithms with prespecified guarantees capable of exploiting additional structure in the objective function.
DOI: 10.1109/cdc.2018.8619183
发表时间: 2018
期刊: 2018 IEEE Conference on Decision and Control (CDC
影响因子: --
作者:
Mohammadi, Hesameddin;Razaviyayn, Meisam;Jovanovic, Mihailo R.
通讯作者: Jovanovic, Mihailo R.
DOI: 10.1109/tac.2016.2582040
发表时间: 2015-03
影响因子: 6.8
作者:
Christian Feller;C. Ebenbauer
通讯作者: Christian Feller;C. Ebenbauer
基于输出反馈的线性系统极限控制
DOI: 10.1109/cdc.2016.7798711
发表时间: 2016
期刊: 2016 IEEE 55th Conference on Decision and Control (CDC)
影响因子: --
作者:
S. Michalowsky;C. Ebenbauer
通讯作者: C. Ebenbauer
DOI: 10.23919/acc45564.2020.9147401
发表时间: 2019-04
期刊: 2020 American Control Conference (ACC)
影响因子: --
作者:
Laurent Lessard;P. Seiler
通讯作者: Laurent Lessard;P. Seiler
DOI: 10.1137/17m1136845
发表时间: 2018-01-01
影响因子: 3.1
作者:
Fazlyab, Mahyar;Ribeiro, Alejandro;Preciado, Victor M.
通讯作者: Preciado, Victor M.