arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07102math.OCmath.DSmath.PRphysics.data-an
收藏

基于Koopman的预测和控制的数据误差界

Finite-data error bounds for Koopman-based prediction and control

Feliks Nüske, Sebastian Peitz, Friedrich Philipp, Manuel Schaller, Karl Worthmann

摘要:

Koopman算子已经成为动态(控制)系统的数据驱动近似的重要工具,例如,通过扩展的动态模式分解。尽管它的流行,收敛结果,特别是,误差界仍然是稀缺的。在本文中,我们推导出概率界的近似误差和预测误差的训练数据点的数量,为普通和随机微分方程,而使用遍历轨迹或独立同分布。样品我们通过一个例子来说明这些界限与Ornstein-Uhlenbeck过程。此外,我们扩展我们的分析(随机)非线性控制仿射系统。我们证明了误差估计以前提出的方法,利用Koopman发电机的线性度,以获得一个双线性代理控制系统,因此,规避了灾难的维数,因为该系统是不是通过增加状态的控制输入。据我们所知,这是第一个有限数据误差分析的随机和/或控制设置。最后,我们证明了双线性方法的有效性,通过比较它与国家的最先进的技术,显示其优越性时,状态和控制耦合。

英文摘要:

The Koopman operator has become an essential tool for data-driven approximation of dynamical (control) systems, e.g., via extended dynamic mode decomposition. Despite its popularity, convergence results and, in particular, error bounds are still scarce. In this paper, we derive probabilistic bounds for the approximation error and the prediction error depending on the number of training data points; for both ordinary and stochastic differential equations while using either ergodic trajectories or i.i.d. samples. We illustrate these bounds by means of an example with the Ornstein-Uhlenbeck process. Moreover, we extend our analysis to (stochastic) nonlinear control-affine systems. We prove error estimates for a previously proposed approach that exploits the linearity of the Koopman generator to obtain a bilinear surrogate control system and, thus, circumvents the curse of dimensionality since the system is not autonomized by augmenting the state by the control inputs. To the best of our knowledge, this is the first finite-data error analysis in the stochastic and/or control setting. Finally, we demonstrate the effectiveness of the bilinear approach by comparing it with state-of-the-art techniques showing its superiority whenever state and control are coupled.

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。

↑