Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ke, Naichang, Tanaka, Ryogo, Kawahara, Yoshinobu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909018506657792
author Ke, Naichang
Tanaka, Ryogo
Kawahara, Yoshinobu
author_facet Ke, Naichang
Tanaka, Ryogo
Kawahara, Yoshinobu
contents We consider an operator-based latent Markov representation of a stochastic nonlinear dynamical system, where the stochastic evolution of the latent state embedded in a reproducing kernel Hilbert space is described with the corresponding transfer operator, and develop a spectral method to learn this representation based on the theory of stochastic realization. The embedding may be learned simultaneously using reproducing kernels, for example, constructed with feed-forward neural networks. We also address the generalization of sequential state-estimation (Kalman filtering) in stochastic nonlinear systems, and of operator-based eigen-mode decomposition of dynamics, for the representation. Several examples with synthetic and real-world data are shown to illustrate the empirical characteristics of our methods, and to investigate the performance of our model in sequential state-estimation and mode decomposition.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators
Ke, Naichang
Tanaka, Ryogo
Kawahara, Yoshinobu
Machine Learning
I.2.6
We consider an operator-based latent Markov representation of a stochastic nonlinear dynamical system, where the stochastic evolution of the latent state embedded in a reproducing kernel Hilbert space is described with the corresponding transfer operator, and develop a spectral method to learn this representation based on the theory of stochastic realization. The embedding may be learned simultaneously using reproducing kernels, for example, constructed with feed-forward neural networks. We also address the generalization of sequential state-estimation (Kalman filtering) in stochastic nonlinear systems, and of operator-based eigen-mode decomposition of dynamics, for the representation. Several examples with synthetic and real-world data are shown to illustrate the empirical characteristics of our methods, and to investigate the performance of our model in sequential state-estimation and mode decomposition.
title Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators
topic Machine Learning
I.2.6
url https://arxiv.org/abs/2501.02721