An Online Algorithm for Smoothed Online Convex Optimization

An Online Algorithm for Smoothed Online Convex Optimization
复制标题

一种在线平滑凸优化算法

DOI:
10.1145/3374888.3374892
复制
发表时间:
2019
期刊:
ACM SIGMETRICS Performance Evaluation Review
影响因子:
--
通讯作者:
A. Wierman
A. Wierman
中科院分区:
--
文献类型:
--
作者:
Gautam Goel;A. Wierman

文献摘要

参考文献

被引文献

相似文献

我们认为在线凸优化(OCO)的设置中的成本是m-强凸的和在线学习者支付切换成本,改变轮之间的决定。我们表明,最近提出的在线平衡下降(OBD)算法是恒定的竞争力,在这种情况下,与竞争比3+O(1/m),无论周围的尺寸。我们证明了我们的方法的一般性,通过显示OBD框架可以用来构建有竞争力的LQR控制算法。
We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio 3+O(1/m), irrespective of the ambient dimension. We demonstrate the generality of our approach by showing that the OBD framework can be used to construct competitive a algorithm for LQR control.
DOI: 10.4230/lipics.approx-random.2015.96
发表时间: 2015
期刊: --
影响因子: --
作者:
N. Bansal;Anupam Gupta;Ravishankar Krishnaswamy;K. Pruhs;Kevin Schewior;C. Stein
通讯作者: N. Bansal;Anupam Gupta;Ravishankar Krishnaswamy;K. Pruhs;Kevin Schewior;C. Stein
快与慢的思考:跨时间尺度的优化分解
DOI: 10.1109/cdc.2017.8263834
发表时间: 2017
期刊: 56th IEEE Conference on Decision and Control
影响因子: --
作者:
Goel, Gautam;Chen, Niangjun;Wierman, Adam
通讯作者: Wierman, Adam