Learning Dynamical Systems by Leveraging Data From Similar Systems

• 成果类型: Article
• 署名作者: Xin, Lei; Ye, Lintao; Chiu, George; Sundaram, Shreyas
• 署名单位: Purdue University System; Purdue University; Chinese University of Hong Kong; Huazhong University of Science & Technology; Purdue University System; Purdue University; Purdue University in Indianapolis; Purdue University System; Purdue University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2025.3543574
• 发表日期: 2025
• 关键词: Consistency; identification; regression

摘要

We consider the problem of learning the dynamics of a linear system when one has access to data generated by an auxiliary system that shares similar (but not identical) dynamics, in addition to data from the true system. We use a weighted least squares approach, and provide a finite sample error bound of the learned model as a function of the number of samples and various system parameters from the two systems as well as the weight assigned to the auxiliary data. We show that the auxiliary data can help to reduce the intrinsic system identification error due to noise, at the price of adding a portion of error that is due to the differences between the two system models. We further provide general guidelines on how to select the weight assigned to the auxiliary system.