Saved in:
Bibliographic Details
Main Author: Grassberger, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.03279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909898687643648
author Grassberger, Peter
author_facet Grassberger, Peter
contents In a recent paper, Jurgens and Crutchfield [Phys. Rev. E {\bf 104}, 064107 (2021), called ``paper III" in the following] computed what they called the ``ambiguity rate" of hidden Markov processes, a concept supposedly introduced by Claude Shannon. This calculation was based on a ``mixed state" formalism introduced by them in J. Stat. Phys. {\bf 183}, 32 (2021) (``paper I"), and developed further in Chaos, {\bf 31}, 083114 (2021) (``paper II"). We point out that (i) ambiguity rates were {\it not} introduced by Shannon; (ii) their computations in paper III are wrong, because of an error made already in papers I and II; (iii) due to this error (a confusion between open sets and their closures), also many of the ``statistical complexity dimensions" computed in II are wrong; (iv) the ``mixed state" formalism of I is just the well known `forward algorithm' for hidden Markov models; (v) the `causal states' in `$ε$-machines' correspond in general to {\it finite} (as opposed to infinite, as often claimed) histories; and (vi) `$ε$-machines' are always countable, in contrast to frequent claims in the literature. In addition, we propose an alternative complexity measure for models where the forecasting complexity is infinite, and we point out that our results apply also beyond hidden Markov models.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03279
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On three papers by Jurgens \& Crutchfield, and on the basic structure of "computational mechanics"
Grassberger, Peter
Statistical Mechanics
In a recent paper, Jurgens and Crutchfield [Phys. Rev. E {\bf 104}, 064107 (2021), called ``paper III" in the following] computed what they called the ``ambiguity rate" of hidden Markov processes, a concept supposedly introduced by Claude Shannon. This calculation was based on a ``mixed state" formalism introduced by them in J. Stat. Phys. {\bf 183}, 32 (2021) (``paper I"), and developed further in Chaos, {\bf 31}, 083114 (2021) (``paper II"). We point out that (i) ambiguity rates were {\it not} introduced by Shannon; (ii) their computations in paper III are wrong, because of an error made already in papers I and II; (iii) due to this error (a confusion between open sets and their closures), also many of the ``statistical complexity dimensions" computed in II are wrong; (iv) the ``mixed state" formalism of I is just the well known `forward algorithm' for hidden Markov models; (v) the `causal states' in `$ε$-machines' correspond in general to {\it finite} (as opposed to infinite, as often claimed) histories; and (vi) `$ε$-machines' are always countable, in contrast to frequent claims in the literature. In addition, we propose an alternative complexity measure for models where the forecasting complexity is infinite, and we point out that our results apply also beyond hidden Markov models.
title On three papers by Jurgens \& Crutchfield, and on the basic structure of "computational mechanics"
topic Statistical Mechanics
url https://arxiv.org/abs/2401.03279