Open Access
Translator Disclaimer
2007 Newton Polytopes of Two-Dimensional Hidden Markov Models
Nigel Boston, Jay Wierer
Experiment. Math. 16(2): 227-238 (2007).

Abstract

In this paper, we show that the Newton polytope of an observation $Y$ from a two-dimensional hidden Markov model\linebreak (2D HMM) lies in a three-dimensional subspace of its ambient eight-dimensional space, whose vertices correspond to the most likely explanations (``hidden'' states) for $Y$ given the model. For each Newton polytope, there exists a set of ``essential'' vertices, which form a skeleton for the polytope. All observations in the same orbit (identical under translations, rotations, and transpositions) have the same Newton polytope. Our main conjecture is that the maximal number of vertices of any Newton polytope is of order $n^2$

Citation

Download Citation

Nigel Boston. Jay Wierer. "Newton Polytopes of Two-Dimensional Hidden Markov Models." Experiment. Math. 16 (2) 227 - 238, 2007.

Information

Published: 2007
First available in Project Euclid: 7 March 2008

zbMATH: 1144.60315
MathSciNet: MR2339278

Subjects:
Primary: 52B12

Keywords: graphical models , Hidden Markov models , Newton polytopes , Tropical geometry

Rights: Copyright © 2007 A K Peters, Ltd.

JOURNAL ARTICLE
12 PAGES


SHARE
Vol.16 • No. 2 • 2007
Back to Top