arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.05423eess.SYcs.LGcs.SYmath.OCstat.ML
收藏

控制的统计学习理论:有限样本视角

Statistical Learning Theory for Control: A Finite Sample Perspective

ETH Zürich(苏黎世联邦理工学院);KTH Royal Institute of Technology(KTH皇家理工学院);University of Pennsylvania(宾夕法尼亚大学)

Anastasios Tsiamis, Ingvar Ziemann, Nikolai Matni, George J. Pappas

AI总结:

本文是一篇有限样本视角的教程综述,自洽梳理统计学习理论在**线性系统辨识**与**LQR学习**中的非渐近结果、核心工具及开放问题。

摘要:

本教程综述概述了与控制和系统辨识相关的统计学习理论在非渐近方面的最新进展。尽管控制的各个领域都已取得实质性进展,但理论在**线性系统辨识**和**线性二次调节器(LQR)学习**方面发展最为成熟,这也是本文的重点。从理论角度看,这些进展背后的大量工作在于改造现代高维统计与学习理论的工具。虽然这些内容对希望整合机器学习工具的控制理论研究者高度相关,但其基础材料往往不易获取。为弥补这一不足,我们对相关材料进行了自洽的阐述,勾勒了支撑近期成果的所有核心思想与技术机制,并提出了若干开放问题与未来方向。

英文摘要:

This tutorial survey provides an overview of recent non-asymptotic advances in statistical learning theory as relevant to control and system identification. While there has been substantial progress across all areas of control, the theory is most well-developed when it comes to linear system identification and learning for the linear quadratic regulator, which are the focus of this manuscript. From a theoretical perspective, much of the labor underlying these advances has been in adapting tools from modern high-dimensional statistics and learning theory. While highly relevant to control theorists interested in integrating tools from machine learning, the foundational material has not always been easily accessible. To remedy this, we provide a self-contained presentation of the relevant material, outlining all the key ideas and the technical machinery that underpin recent results. We also present a number of open problems and future directions.

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。

↑