Discussion of the papers by Rissanen, and by Wallace and Dowe

B. Clarke

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Commenting on the papers by Dr Rissanen and Professors Wallace and Dowe is a daunting sort of pleasure. Superficially, the papers are not closely related: Dr Rissanen has focused on the Shtarkov optimality criterion in a minimum description length (MDL) context giving some new implications from normalization (see his equation (1)) for model selection and hypothesis testing. By contrast, Wallace and Dowe have given a first, and welcome, effort to axiomatize a setting in which it is reasonable to hope that the algorithmic complexity approaches of Kolmogorov and Solomonoff - streams one and two, using UTMs - may coincide with the Shannon theory approaches - stream three in its minimum message length (MML) and MDL versions. Despite these differences, there are several senses in which these two papers are closely related.

Original languageEnglish (US)
Pages (from-to)338-339
Number of pages2
JournalComputer Journal
Volume42
Issue number4
DOIs
StatePublished - Jan 1 1999

Fingerprint

Testing

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Discussion of the papers by Rissanen, and by Wallace and Dowe. / Clarke, B.

In: Computer Journal, Vol. 42, No. 4, 01.01.1999, p. 338-339.

Research output: Contribution to journalArticle

Clarke, B. / Discussion of the papers by Rissanen, and by Wallace and Dowe. In: Computer Journal. 1999 ; Vol. 42, No. 4. pp. 338-339.
@article{b48b2f495b51431a95ecf92d94d0e68e,
title = "Discussion of the papers by Rissanen, and by Wallace and Dowe",
abstract = "Commenting on the papers by Dr Rissanen and Professors Wallace and Dowe is a daunting sort of pleasure. Superficially, the papers are not closely related: Dr Rissanen has focused on the Shtarkov optimality criterion in a minimum description length (MDL) context giving some new implications from normalization (see his equation (1)) for model selection and hypothesis testing. By contrast, Wallace and Dowe have given a first, and welcome, effort to axiomatize a setting in which it is reasonable to hope that the algorithmic complexity approaches of Kolmogorov and Solomonoff - streams one and two, using UTMs - may coincide with the Shannon theory approaches - stream three in its minimum message length (MML) and MDL versions. Despite these differences, there are several senses in which these two papers are closely related.",
author = "B. Clarke",
year = "1999",
month = "1",
day = "1",
doi = "10.1093/comjnl/42.4.338",
language = "English (US)",
volume = "42",
pages = "338--339",
journal = "Computer Journal",
issn = "0010-4620",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Discussion of the papers by Rissanen, and by Wallace and Dowe

AU - Clarke, B.

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Commenting on the papers by Dr Rissanen and Professors Wallace and Dowe is a daunting sort of pleasure. Superficially, the papers are not closely related: Dr Rissanen has focused on the Shtarkov optimality criterion in a minimum description length (MDL) context giving some new implications from normalization (see his equation (1)) for model selection and hypothesis testing. By contrast, Wallace and Dowe have given a first, and welcome, effort to axiomatize a setting in which it is reasonable to hope that the algorithmic complexity approaches of Kolmogorov and Solomonoff - streams one and two, using UTMs - may coincide with the Shannon theory approaches - stream three in its minimum message length (MML) and MDL versions. Despite these differences, there are several senses in which these two papers are closely related.

AB - Commenting on the papers by Dr Rissanen and Professors Wallace and Dowe is a daunting sort of pleasure. Superficially, the papers are not closely related: Dr Rissanen has focused on the Shtarkov optimality criterion in a minimum description length (MDL) context giving some new implications from normalization (see his equation (1)) for model selection and hypothesis testing. By contrast, Wallace and Dowe have given a first, and welcome, effort to axiomatize a setting in which it is reasonable to hope that the algorithmic complexity approaches of Kolmogorov and Solomonoff - streams one and two, using UTMs - may coincide with the Shannon theory approaches - stream three in its minimum message length (MML) and MDL versions. Despite these differences, there are several senses in which these two papers are closely related.

UR - http://www.scopus.com/inward/record.url?scp=0032672788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032672788&partnerID=8YFLogxK

U2 - 10.1093/comjnl/42.4.338

DO - 10.1093/comjnl/42.4.338

M3 - Article

AN - SCOPUS:0032672788

VL - 42

SP - 338

EP - 339

JO - Computer Journal

JF - Computer Journal

SN - 0010-4620

IS - 4

ER -