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 1903.09122cs.LGcs.SYeess.SYmath.OCstat.ML
收藏

随机系统辨识的有限样本分析

Finite Sample Analysis of Stochastic System Identification

Department of Electrical and Systems Engineering, University of Pennsylvania(宾夕法尼亚大学电气与系统工程系)

Anastasios Tsiamis, George J. Pappas

AI总结:

本文基于机器学习和统计学的现代工具,研究了随机系统辨识的有限样本复杂性。通过子空间辨识算法和有限数量的输出样本,提供了系统参数估计误差的非渐近高概率上界,证明了在高概率下估计误差以1/√N的速度减小。

摘要:

在本文中,我们利用现代机器学习和统计学工具,分析了随机系统辨识的有限样本复杂性。一个未知的离散时间线性系统在高斯噪声下随时间演变,没有外部输入。目标是在给定有限时间跨度N内的单条输出测量轨迹的情况下,恢复系统参数以及卡尔曼滤波增益。基于子空间辨识算法和有限数量的N个输出样本,我们提供了系统参数估计误差的非渐近高概率上界。我们的分析利用了最近的随机矩阵理论、自归一化鞅和SVD鲁棒性结果,以证明在高概率下估计误差以1/√N的速度减小。我们的非渐近界不仅与经典渐近结果一致,而且即使在系统处于临界稳定的情况下也有效。

英文摘要:

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without external inputs. The objective is to recover the system parameters as well as the Kalman filter gain, given a single trajectory of output measurements over a finite horizon of length $N$. Based on a subspace identification algorithm and a finite number of $N$ output samples, we provide non-asymptotic high-probability upper bounds for the system parameter estimation errors. Our analysis uses recent results from random matrix theory, self-normalized martingales and SVD robustness, in order to show that with high probability the estimation errors decrease with a rate of $1/\sqrt{N}$. Our non-asymptotic bounds not only agree with classical asymptotic results, but are also valid even when the system is marginally stable.

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。

↑