|国家预印本平台
首页|Data-Efficient System Identification via Lipschitz Neural Networks

Data-Efficient System Identification via Lipschitz Neural Networks

Data-Efficient System Identification via Lipschitz Neural Networks

来源:Arxiv_logoArxiv
英文摘要

Extracting dynamic models from data is of enormous importance in understanding the properties of unknown systems. In this work, we employ Lipschitz neural networks, a class of neural networks with a prescribed upper bound on their Lipschitz constant, to address the problem of data-efficient nonlinear system identification. Under the (fairly weak) assumption that the unknown system is Lipschitz continuous, we propose a method to estimate the approximation error bound of the trained network and the bound on the difference between the simulated trajectories by the trained models and the true system. Empirical results show that our method outperforms classic fully connected neural networks and Lipschitz regularized networks through simulation studies on three dynamical systems, and the advantage of our method is more noticeable when less data is used for training.

Shiqing Wei、Farshad Khorrami、Prashanth Krishnamurthy

自动化基础理论计算技术、计算机技术

Shiqing Wei,Farshad Khorrami,Prashanth Krishnamurthy.Data-Efficient System Identification via Lipschitz Neural Networks[EB/OL].(2025-08-20)[2025-09-02].https://arxiv.org/abs/2410.21234.点此复制

评论