Discriminative k-metrics

Arthur Szlam; Guillermo Sapiro

doi:10.1145/1553374.1553503

Discriminative k-metrics

Arthur Szlam, Guillermo Sapiro

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Scopus citations

Abstract

The k q-flats algorithm is a generalization of the popular k-means algorithm where q dimensional best fit affine sets replace centroids as the cluster prototypes. In this work, a modification of the k q-flats framework for pattern classification is introduced. The basic idea is to replace the original reconstruction only energy, which is optimized to obtain the k affine spaces, by a new energy that incorporates discriminative terms. This way, the actual classification task is introduced as part of the design and optimization. The presentation of the proposed framework is complemented with experimental results, showing that the method is computationally very efficient and gives excellent results on standard supervised learning benchmarks.

Original language	English (US)
Title of host publication	Proceedings of the 26th International Conference On Machine Learning, ICML 2009
Publisher	Omnipress
Pages	1009-1016
Number of pages	8
ISBN (Print)	9781605585161
DOIs	https://doi.org/10.1145/1553374.1553503
State	Published - 2009
Externally published	Yes
Event	26th International Conference On Machine Learning, ICML 2009 - Montreal, QC, Canada Duration: Jun 14 2009 → Jun 18 2009

Publication series

Name	Proceedings of the 26th International Conference On Machine Learning, ICML 2009

Other

Other	26th International Conference On Machine Learning, ICML 2009
Country/Territory	Canada
City	Montreal, QC
Period	6/14/09 → 6/18/09

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Software

Access to Document

10.1145/1553374.1553503

Cite this

@inproceedings{eed89090f2b3453198c5ca600042ccac,

title = "Discriminative k-metrics",

abstract = "The k q-flats algorithm is a generalization of the popular k-means algorithm where q dimensional best fit affine sets replace centroids as the cluster prototypes. In this work, a modification of the k q-flats framework for pattern classification is introduced. The basic idea is to replace the original reconstruction only energy, which is optimized to obtain the k affine spaces, by a new energy that incorporates discriminative terms. This way, the actual classification task is introduced as part of the design and optimization. The presentation of the proposed framework is complemented with experimental results, showing that the method is computationally very efficient and gives excellent results on standard supervised learning benchmarks.",

author = "Arthur Szlam and Guillermo Sapiro",

year = "2009",

doi = "10.1145/1553374.1553503",

language = "English (US)",

isbn = "9781605585161",

series = "Proceedings of the 26th International Conference On Machine Learning, ICML 2009",

publisher = "Omnipress",

pages = "1009--1016",

booktitle = "Proceedings of the 26th International Conference On Machine Learning, ICML 2009",

note = "26th International Conference On Machine Learning, ICML 2009 ; Conference date: 14-06-2009 Through 18-06-2009",

}

Szlam, A & Sapiro, G 2009, Discriminative k-metrics. in Proceedings of the 26th International Conference On Machine Learning, ICML 2009. Proceedings of the 26th International Conference On Machine Learning, ICML 2009, Omnipress, pp. 1009-1016, 26th International Conference On Machine Learning, ICML 2009, Montreal, QC, Canada, 6/14/09. https://doi.org/10.1145/1553374.1553503

TY - GEN

T1 - Discriminative k-metrics

AU - Szlam, Arthur

AU - Sapiro, Guillermo

PY - 2009

Y1 - 2009

N2 - The k q-flats algorithm is a generalization of the popular k-means algorithm where q dimensional best fit affine sets replace centroids as the cluster prototypes. In this work, a modification of the k q-flats framework for pattern classification is introduced. The basic idea is to replace the original reconstruction only energy, which is optimized to obtain the k affine spaces, by a new energy that incorporates discriminative terms. This way, the actual classification task is introduced as part of the design and optimization. The presentation of the proposed framework is complemented with experimental results, showing that the method is computationally very efficient and gives excellent results on standard supervised learning benchmarks.

AB - The k q-flats algorithm is a generalization of the popular k-means algorithm where q dimensional best fit affine sets replace centroids as the cluster prototypes. In this work, a modification of the k q-flats framework for pattern classification is introduced. The basic idea is to replace the original reconstruction only energy, which is optimized to obtain the k affine spaces, by a new energy that incorporates discriminative terms. This way, the actual classification task is introduced as part of the design and optimization. The presentation of the proposed framework is complemented with experimental results, showing that the method is computationally very efficient and gives excellent results on standard supervised learning benchmarks.

UR - https://www.scopus.com/pages/publications/70449467348

UR - https://www.scopus.com/inward/citedby.url?scp=70449467348&partnerID=8YFLogxK

U2 - 10.1145/1553374.1553503

DO - 10.1145/1553374.1553503

M3 - Conference contribution

AN - SCOPUS:70449467348

SN - 9781605585161

T3 - Proceedings of the 26th International Conference On Machine Learning, ICML 2009

SP - 1009

EP - 1016

BT - Proceedings of the 26th International Conference On Machine Learning, ICML 2009

PB - Omnipress

T2 - 26th International Conference On Machine Learning, ICML 2009

Y2 - 14 June 2009 through 18 June 2009

ER -

Discriminative k-metrics

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this