Probability model type sufficiency

Leigh James Fitzgibbon; Lloyd Allison; Joshua William Comley

doi:10.1007/978-3-540-45080-1_72

Probability model type sufficiency

Leigh James Fitzgibbon, Lloyd Allison, Joshua William Comley

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

We investigate the role of sufficient statistics in generalized probabilistic data mining and machine learning software frameworks. Some issues involved in the specification of a statistical model type are discussed and we show that it is beneficial to explicitly include a sufficient statistic and functions for its manipulation in the model type’s specification. Instances of such types can then be used by generalized learning algorithms while maintaining optimal learning time complexity. Examples are given for problems such as incremental learning and data partitioning problems (e.g. change-point problems, decision trees and mixture models).

Original language	English
Title of host publication	Intelligent Data Engineering and Automated Learning
Subtitle of host publication	4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers
Editors	Jiming Liu, Yiuming Cheung, Hujun Yin
Place of Publication	New York NY USA
Publisher	Springer
Pages	530-534
Number of pages	5
ISBN (Electronic)	9783540450801
ISBN (Print)	9783540405504
DOIs	https://doi.org/10.1007/978-3-540-45080-1_72
Publication status	Published - 2003
Event	International Conference on Intelligent Data Engineering and Automated Learning 2003 - Hong Kong China, New York USA Duration: 1 Jan 2003 → …

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	2690
ISSN (Print)	0302-9743

Conference

Conference	International Conference on Intelligent Data Engineering and Automated Learning 2003
City	New York USA
Period	1/01/03 → …

Access to Document

10.1007/978-3-540-45080-1_72

Cite this

Fitzgibbon, L. J., Allison, L., & Comley, J. W. (2003). Probability model type sufficiency. In J. Liu, Y. Cheung, & H. Yin (Eds.), Intelligent Data Engineering and Automated Learning: 4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers (pp. 530-534). (Lecture Notes in Computer Science; Vol. 2690). Springer. https://doi.org/10.1007/978-3-540-45080-1_72

Fitzgibbon, Leigh James ; Allison, Lloyd ; Comley, Joshua William. / Probability model type sufficiency. Intelligent Data Engineering and Automated Learning: 4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers. editor / Jiming Liu ; Yiuming Cheung ; Hujun Yin. New York NY USA : Springer, 2003. pp. 530-534 (Lecture Notes in Computer Science).

@inproceedings{6e9bcdc4d8c84bf29b6ac8c1ceab4c42,

title = "Probability model type sufficiency",

abstract = "We investigate the role of sufficient statistics in generalized probabilistic data mining and machine learning software frameworks. Some issues involved in the specification of a statistical model type are discussed and we show that it is beneficial to explicitly include a sufficient statistic and functions for its manipulation in the model type{\textquoteright}s specification. Instances of such types can then be used by generalized learning algorithms while maintaining optimal learning time complexity. Examples are given for problems such as incremental learning and data partitioning problems (e.g. change-point problems, decision trees and mixture models).",

author = "Fitzgibbon, {Leigh James} and Lloyd Allison and Comley, {Joshua William}",

year = "2003",

doi = "10.1007/978-3-540-45080-1_72",

language = "English",

isbn = "9783540405504",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "530--534",

editor = "Jiming Liu and Yiuming Cheung and Hujun Yin",

booktitle = "Intelligent Data Engineering and Automated Learning",

note = "International Conference on Intelligent Data Engineering and Automated Learning 2003 ; Conference date: 01-01-2003",

}

Fitzgibbon, LJ, Allison, L & Comley, JW 2003, Probability model type sufficiency. in J Liu, Y Cheung & H Yin (eds), Intelligent Data Engineering and Automated Learning: 4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers. Lecture Notes in Computer Science, vol. 2690, Springer, New York NY USA, pp. 530-534, International Conference on Intelligent Data Engineering and Automated Learning 2003, New York USA, 1/01/03. https://doi.org/10.1007/978-3-540-45080-1_72

Probability model type sufficiency. / Fitzgibbon, Leigh James; Allison, Lloyd; Comley, Joshua William.
Intelligent Data Engineering and Automated Learning: 4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers. ed. / Jiming Liu; Yiuming Cheung; Hujun Yin. New York NY USA: Springer, 2003. p. 530-534 (Lecture Notes in Computer Science; Vol. 2690).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Probability model type sufficiency

AU - Fitzgibbon, Leigh James

AU - Allison, Lloyd

AU - Comley, Joshua William

PY - 2003

Y1 - 2003

N2 - We investigate the role of sufficient statistics in generalized probabilistic data mining and machine learning software frameworks. Some issues involved in the specification of a statistical model type are discussed and we show that it is beneficial to explicitly include a sufficient statistic and functions for its manipulation in the model type’s specification. Instances of such types can then be used by generalized learning algorithms while maintaining optimal learning time complexity. Examples are given for problems such as incremental learning and data partitioning problems (e.g. change-point problems, decision trees and mixture models).

AB - We investigate the role of sufficient statistics in generalized probabilistic data mining and machine learning software frameworks. Some issues involved in the specification of a statistical model type are discussed and we show that it is beneficial to explicitly include a sufficient statistic and functions for its manipulation in the model type’s specification. Instances of such types can then be used by generalized learning algorithms while maintaining optimal learning time complexity. Examples are given for problems such as incremental learning and data partitioning problems (e.g. change-point problems, decision trees and mixture models).

U2 - 10.1007/978-3-540-45080-1_72

DO - 10.1007/978-3-540-45080-1_72

M3 - Conference Paper

SN - 9783540405504

T3 - Lecture Notes in Computer Science

SP - 530

EP - 534

BT - Intelligent Data Engineering and Automated Learning

A2 - Liu, Jiming

A2 - Cheung, Yiuming

A2 - Yin, Hujun

PB - Springer

CY - New York NY USA

T2 - International Conference on Intelligent Data Engineering and Automated Learning 2003

Y2 - 1 January 2003

ER -

Fitzgibbon LJ, Allison L, Comley JW. Probability model type sufficiency. In Liu J, Cheung Y, Yin H, editors, Intelligent Data Engineering and Automated Learning: 4th International Conference, IDEAL 2003 Hong Kong, China, March 21–23, 2003 Revised Papers. New York NY USA: Springer. 2003. p. 530-534. (Lecture Notes in Computer Science). doi: 10.1007/978-3-540-45080-1_72