English

On Computing the Total Variation Distance of Hidden Markov Models

Formal Languages and Automata Theory 2018-04-18 v1 Logic in Computer Science

Abstract

We prove results on the decidability and complexity of computing the total variation distance (equivalently, the L1L_1-distance) of hidden Markov models (equivalently, labelled Markov chains). This distance measures the difference between the distributions on words that two hidden Markov models induce. The main results are: (1) it is undecidable whether the distance is greater than a given threshold; (2) approximation is #P-hard and in PSPACE.

Keywords

Cite

@article{arxiv.1804.06170,
  title  = {On Computing the Total Variation Distance of Hidden Markov Models},
  author = {Stefan Kiefer},
  journal= {arXiv preprint arXiv:1804.06170},
  year   = {2018}
}

Comments

Technical report for an ICALP'18 paper

R2 v1 2026-06-23T01:26:13.831Z