arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11899eess.SYcs.SY
收藏

基于梯度的自适应预测与控制非线性动力系统

Gradient-Based Adaptive Prediction and Control for Nonlinear Dynamical Systems

Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)

Yujing Liu, Xin Zheng, Zhixin Liu, Lei Guo

AI总结:

本文提出基于梯度的自适应预测与控制方法,用于非线性随机动力系统,通过弱凸性条件实现全局收敛,并在实测数据和仿真中验证其有效性。

摘要:

本文研究了在预测基于损失的弱凸性条件下,非线性随机动力系统中基于梯度的自适应预测与控制。该条件涵盖了控制和机器学习中的广泛非线性模型,如饱和函数、sigmoid、ReLU和tanh激活函数,以及标准分类模型。无需数据的持续激励,我们建立了所提出的自适应预测器的全局收敛性,并推导了其渐近性能的显式速率。此外,在经典非线性最小相位条件和非线性项的线性增长界下,我们建立了由此产生的闭环控制误差的收敛速率。最后,我们在现实世界的司法量刑数据集上展示了所提出的自适应预测算法的有效性。自适应控制性能还将通过数值模拟进行评估。

英文摘要:

This paper investigates gradient-based adaptive prediction and control for nonlinear stochastic dynamical systems under a weak convexity condition on the prediction-based loss. This condition accommodates a broad range of nonlinear models in control and machine learning such as saturation functions, sigmoid, ReLU and tanh activation functions, and standard classification models. Without requiring any persistent excitation of the data, we establish global convergence of the proposed adaptive predictor and derive explicit rates for its asymptotic performance. Furthermore, under a classical nonlinear minimum-phase condition and with a linear growth bound on the nonlinearities, we establish the convergence rate of the resulting closed-loop control error. Finally, we demonstrate the effectiveness of the proposed adaptive prediction algorithm on a real-world judicial sentencing dataset. The adaptive control performance will also be evaluated via a numerical simulation.

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。

↑