Learning Mixtures of Linear Dynamical Systems
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Time SeriesTime Series AnalysisSimilar Papers 제목 키워드 기반
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
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 SeriesFinite Sample Analysis of Tensor Decomposition for Learning Mixtures of Linear Systems
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 DecompositionPhysics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics
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
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
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…