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 2312.15340eess.SYcs.LGcs.SY
收藏

基于元学习的动态系统自适应稳定性证书

Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems

Texas A&M University(德克萨斯A&M大学)

Amit Jena, Dileep Kalathil, Le Xie

AI总结:

针对参数变化下神经李雅普诺夫函数难以适应的问题,提出将模型无关元学习与NLF结合,训练元函数以自适应参数变化,在基准系统上验证了稳定性评估性能。

摘要:

本文研究了动态系统中基于神经网络(NN)的自适应稳定性认证问题。现有最先进的方法,如神经李雅普诺夫函数(NLFs),利用基于神经网络的公式来评估非线性动态系统的稳定性,并在状态空间中计算吸引域(ROA)。然而,在参数不确定性下,如果系统参数值随时间变化,NLF方法无法适应此类变化,可能导致保守的稳定性评估性能。我们通过将模型无关元学习(MAML)与NLF相结合来规避这一问题,并提出了元NLF(meta-NLFs)。在此过程中,我们训练一个元函数,使其适应任何参数变化,并在新的测试时参数值下更新为系统的NLF。我们在一些标准基准自主动态系统上展示了元NLF的稳定性评估性能。

英文摘要:

This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. The state-of-the-art methods, such as Neural Lyapunov Functions (NLFs), use NN-based formulations to assess the stability of a non-linear dynamical system and compute a Region of Attraction (ROA) in the state space. However, under parametric uncertainty, if the values of system parameters vary over time, the NLF methods fail to adapt to such changes and may lead to conservative stability assessment performance. We circumvent this issue by integrating Model Agnostic Meta-learning (MAML) with NLFs and propose meta-NLFs. In this process, we train a meta-function that adapts to any parametric shifts and updates into an NLF for the system with new test-time parameter values. We demonstrate the stability assessment performance of meta-NLFs on some standard benchmark autonomous dynamical systems.

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。

↑