arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03934eess.SYcs.SYmath.DSmath.OC
收藏

学习Koopman算子的凸优化方法

A Convex Optimization Approach to Learning Koopman Operators

Mario Sznaier

摘要:

Koopman算子提供了学习非线性动力学的线性近似的易处理的手段。已经提出了许多方法来找到这些运营商,通常基于近似使用先验固定类的模型。然而,选择合适的模型和边界的近似误差是远远不够的。出于这些困难,在本文中,我们提出了一种基于优化的方法来学习Koopman算子的数据。我们的结果表明,Koopman算子,相关的Hilbert空间的观测量和一个合适的字典可以通过解决两个秩约束半定规划(SDP)。虽然原则上这些问题是NP难的,但使用秩的标准松弛会导致凸SDP。此外,这些SDP表现出弦稀疏性,导致算法与数据点的数量线性缩放。

英文摘要:

Koopman operators provide tractable means of learning linear approximations of non-linear dynamics. Many approaches have been proposed to find these operators, typically based upon approximations using an a-priori fixed class of models. However, choosing appropriate models and bounding the approximation error is far from trivial. Motivated by these difficulties, in this paper we propose an optimization based approach to learning Koopman operators from data. Our results show that the Koopman operator, the associated Hilbert space of observables and a suitable dictionary can be obtained by solving two rank-constrained semi-definite programs (SDP). While in principle these problems are NP-hard, the use of standard relaxations of rank leads to convex SDPs. Further, these SDPs exhibit chordal sparsity leading to algorithms that scale linearly with the number of data points.

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。

↑