paper-with-me

홈 › Papers

Learning Mixtures of Linear Dynamical Systems

2022-01-26 · Yanxi Chen, H. Vincent Poor

We study the problem of learning a mixture of multiple linear dynamical systems (LDSs) from unlabeled short sample trajectories, each generated by one of the LDS models. Despite the wide applicability of mixture models for time-series data, learning algorithms that come with end-to-end performance guarantees are largely absent from existing literature. There are multiple sources of technical challenges, including but not limited to (1) the presence of latent variables (i.e. the unknown labels of trajectories); (2) the possibility that the sample trajectories might have lengths much smaller than the dimension $d$ of the LDS models; and (3) the complicated temporal dependence inherent to time-series data. To tackle these challenges, we develop a two-stage meta-algorithm, which is guaranteed to efficiently recover each ground-truth LDS model up to error $\tilde{O}(\sqrt{d/T})$, where $T$ is the total sample size. We validate our theoretical studies with numerical experiments, confirming the efficacy of the proposed algorithm.

📄 PDF Abstract BibTeX arXiv:2201.11211

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems

2023-07-13 · Ainesh Bakshi, Allen Liu, Ankur Moitra, Morris Yau

Recently Chen and Poor initiated the study of learning mixtures of linear dynamical systems. While linear dynamical systems already have wide-ranging applications in modeling time-series data, using mixture models can le…

Tensor DecompositionTime Series

Finite Sample Analysis of Tensor Decomposition for Learning Mixtures of Linear Systems

2024-12-13 · Maryann Rui, Munther Dahleh

We study the problem of learning mixtures of linear dynamical systems (MLDS) from input-output data. The mixture setting allows us to leverage observations from related dynamical systems to improve the estimation of indi…

Tensor Decomposition

Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics

2026-06-09 · Vijay Yadav, Madhu Priya, Manish Dev Shrimali, Prabhat K. Jaiswal arxiv

The spatiotemporal evolution of many physical, chemical, and biological systems is described by nonlinear partial differential equations (PDEs). Recently, deep neural network-based surrogate models have gained increasing…

Learning Mixtures of Linear Dynamical Systems via Hybrid Tensor-EM Method

2025-10-07 · Lulu Gong, Shreya Saxena arxiv

Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings…

On the robust learning mixtures of linear regressions

2023-05-23 · Ying Huang, Liang Chen

In this note, we consider the problem of robust learning mixtures of linear regressions. We connect mixtures of linear regressions and mixtures of Gaussians with a simple thresholding, so that a quasi-polynomial time alg…