English

Sparse Linear Dynamical System with Its Application in Multivariate Clinical Time Series

Artificial Intelligence 2013-12-04 v2 Machine Learning Machine Learning

Abstract

Linear Dynamical System (LDS) is an elegant mathematical framework for modeling and learning multivariate time series. However, in general, it is difficult to set the dimension of its hidden state space. A small number of hidden states may not be able to model the complexities of a time series, while a large number of hidden states can lead to overfitting. In this paper, we study methods that impose an 1\ell_1 regularization on the transition matrix of an LDS model to alleviate the problem of choosing the optimal number of hidden states. We incorporate a generalized gradient descent method into the Maximum a Posteriori (MAP) framework and use Expectation Maximization (EM) to iteratively achieve sparsity on the transition matrix of an LDS model. We show that our Sparse Linear Dynamical System (SLDS) improves the predictive performance when compared to ordinary LDS on a multivariate clinical time series dataset.

Keywords

Cite

@article{arxiv.1311.7071,
  title  = {Sparse Linear Dynamical System with Its Application in Multivariate Clinical Time Series},
  author = {Zitao Liu and Milos Hauskrecht},
  journal= {arXiv preprint arXiv:1311.7071},
  year   = {2013}
}

Comments

Appear in Neural Information Processing Systems(NIPS) Workshop on Machine Learning for Clinical Data Analysis and Healthcare 2013

R2 v1 2026-06-22T02:16:13.538Z