Learning Parametric-Output HMMs with Two Aliased States

Abstract

In various applications involving hidden Markov models (HMMs), some of the hidden states are aliased, having identical output distributions. The minimality, identifiability and learnability of such aliased HMMs have been long standing problems, with only partial solutions provided thus far. In this paper we focus on parametric-output HMMs, whose output distributions come from a parametric family, and that have exactly two aliased states. For this class, we present a complete characterization of their minimality and identifiability. Furthermore, for a large family of parametric output distributions, we derive computationally efficient and statistically consistent algorithms to detect the presence of aliasing and learn the aliased HMM transition and emission parameters. We illustrate our theoretical analysis by several simulations.

Cite

Text

Weiss and Nadler. "Learning Parametric-Output HMMs with Two Aliased States." International Conference on Machine Learning, 2015.

Markdown

[Weiss and Nadler. "Learning Parametric-Output HMMs with Two Aliased States." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/weiss2015icml-learning/)

BibTeX

@inproceedings{weiss2015icml-learning,
  title     = {{Learning Parametric-Output HMMs with Two Aliased States}},
  author    = {Weiss, Roi and Nadler, Boaz},
  booktitle = {International Conference on Machine Learning},
  year      = {2015},
  pages     = {635-644},
  volume    = {37},
  url       = {https://mlanthology.org/icml/2015/weiss2015icml-learning/}
}