Random projection towards the Baire metric for high dimensional clustering

Fionn Murtagh, Pedro Contreras

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

For high dimensional clustering and proximity finding, also referred to as high dimension and low sample size data, we use random projection with the following principle. With the greater probability of close-to-orthogonal projections, compared to orthogonal projections, we can use rank order sensitivity of projected values. Our Baire metric, divisive hierarchical clustering, is of linear computation time.

LanguageEnglish
Title of host publicationStatistical Learning and Data Sciences
Subtitle of host publicationThird International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings
EditorsAlexander Gammerman, Vladimir Vovk, Harris Papadopoulos
PublisherSpringer Verlag
Pages424-431
Number of pages8
ISBN (Electronic)9783319170916
ISBN (Print)9783319170909
DOIs
Publication statusPublished - 3 Apr 2015
Externally publishedYes
Event3rd International Symposium on Statistical Learning and Data Sciences - University of London, Egham, United Kingdom
Duration: 20 Apr 201523 Apr 2015
Conference number: 3
http://www.clrc.rhul.ac.uk/slds2015/ (Link to Conference Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume9047
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference3rd International Symposium on Statistical Learning and Data Sciences
Abbreviated titleSLDS 2015
CountryUnited Kingdom
CityEgham
Period20/04/1523/04/15
Internet address

Fingerprint

Random Projection
Orthogonal Projection
High-dimensional
Clustering
Metric
Rank order
Hierarchical Clustering
Proximity
Higher Dimensions
Sample Size

Cite this

Murtagh, F., & Contreras, P. (2015). Random projection towards the Baire metric for high dimensional clustering. In A. Gammerman, V. Vovk, & H. Papadopoulos (Eds.), Statistical Learning and Data Sciences : Third International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings (pp. 424-431). (Lecture Notes in Computer Science; Vol. 9047). Springer Verlag. https://doi.org/10.1007/978-3-319-17091-6_37
Murtagh, Fionn ; Contreras, Pedro. / Random projection towards the Baire metric for high dimensional clustering. Statistical Learning and Data Sciences : Third International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings. editor / Alexander Gammerman ; Vladimir Vovk ; Harris Papadopoulos. Springer Verlag, 2015. pp. 424-431 (Lecture Notes in Computer Science).
@inproceedings{5fba038ead2f4ea39a828e0116b71430,
title = "Random projection towards the Baire metric for high dimensional clustering",
abstract = "For high dimensional clustering and proximity finding, also referred to as high dimension and low sample size data, we use random projection with the following principle. With the greater probability of close-to-orthogonal projections, compared to orthogonal projections, we can use rank order sensitivity of projected values. Our Baire metric, divisive hierarchical clustering, is of linear computation time.",
keywords = "Big data, Binary rooted tree, Computational complexity, Hierarchical clustering, Ultrametric topology",
author = "Fionn Murtagh and Pedro Contreras",
year = "2015",
month = "4",
day = "3",
doi = "10.1007/978-3-319-17091-6_37",
language = "English",
isbn = "9783319170909",
series = "Lecture Notes in Computer Science",
publisher = "Springer Verlag",
pages = "424--431",
editor = "Alexander Gammerman and Vladimir Vovk and Harris Papadopoulos",
booktitle = "Statistical Learning and Data Sciences",

}

Murtagh, F & Contreras, P 2015, Random projection towards the Baire metric for high dimensional clustering. in A Gammerman, V Vovk & H Papadopoulos (eds), Statistical Learning and Data Sciences : Third International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings. Lecture Notes in Computer Science, vol. 9047, Springer Verlag, pp. 424-431, 3rd International Symposium on Statistical Learning and Data Sciences, Egham, United Kingdom, 20/04/15. https://doi.org/10.1007/978-3-319-17091-6_37

Random projection towards the Baire metric for high dimensional clustering. / Murtagh, Fionn; Contreras, Pedro.

Statistical Learning and Data Sciences : Third International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings. ed. / Alexander Gammerman; Vladimir Vovk; Harris Papadopoulos. Springer Verlag, 2015. p. 424-431 (Lecture Notes in Computer Science; Vol. 9047).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Random projection towards the Baire metric for high dimensional clustering

AU - Murtagh, Fionn

AU - Contreras, Pedro

PY - 2015/4/3

Y1 - 2015/4/3

N2 - For high dimensional clustering and proximity finding, also referred to as high dimension and low sample size data, we use random projection with the following principle. With the greater probability of close-to-orthogonal projections, compared to orthogonal projections, we can use rank order sensitivity of projected values. Our Baire metric, divisive hierarchical clustering, is of linear computation time.

AB - For high dimensional clustering and proximity finding, also referred to as high dimension and low sample size data, we use random projection with the following principle. With the greater probability of close-to-orthogonal projections, compared to orthogonal projections, we can use rank order sensitivity of projected values. Our Baire metric, divisive hierarchical clustering, is of linear computation time.

KW - Big data

KW - Binary rooted tree

KW - Computational complexity

KW - Hierarchical clustering

KW - Ultrametric topology

UR - http://www.scopus.com/inward/record.url?scp=84949776887&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-17091-6_37

DO - 10.1007/978-3-319-17091-6_37

M3 - Conference contribution

SN - 9783319170909

T3 - Lecture Notes in Computer Science

SP - 424

EP - 431

BT - Statistical Learning and Data Sciences

A2 - Gammerman, Alexander

A2 - Vovk, Vladimir

A2 - Papadopoulos, Harris

PB - Springer Verlag

ER -

Murtagh F, Contreras P. Random projection towards the Baire metric for high dimensional clustering. In Gammerman A, Vovk V, Papadopoulos H, editors, Statistical Learning and Data Sciences : Third International Symposium, SLDS 2015, Egham, UK, April 20-23, 2015, Proceedings. Springer Verlag. 2015. p. 424-431. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-17091-6_37