Efficient dimensionality reduction for canonical correlation analysis

Haim Avron; Christos Boutsidis; Sivan Toledo; Anastasios Zouzias

Efficient dimensionality reduction for canonical correlation analysis

Haim Avron, Christos Boutsidis, Sivan Toledo, Anastasios Zouzias

School of Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

We present a fast algorithm for approximate Canonical Correlation Analysis (CCA). Given a pair of tall-and-thin matrices, the proposed algorithm first employs a randomized dimensionality reduction transform to reduce the size of the input matrices, and then applies any standard CCA algorithm to the new pair of matrices. The algorithm computes an approximate CCA to the original pair of matrices with provable guarantees, while requiring asymptotically less operations than the state-of-the-art exact algorithms.

Original language	English
Pages	347-355
Number of pages	9
State	Published - 2013
Event	30th International Conference on Machine Learning, ICML 2013 - Atlanta, GA, United States Duration: 16 Jun 2013 → 21 Jun 2013

Conference

Conference	30th International Conference on Machine Learning, ICML 2013
Country/Territory	United States
City	Atlanta, GA
Period	16/06/13 → 21/06/13

Cite this

@conference{82035d9f42b2433a9882a1dde742690d,

title = "Efficient dimensionality reduction for canonical correlation analysis",

abstract = "We present a fast algorithm for approximate Canonical Correlation Analysis (CCA). Given a pair of tall-and-thin matrices, the proposed algorithm first employs a randomized dimensionality reduction transform to reduce the size of the input matrices, and then applies any standard CCA algorithm to the new pair of matrices. The algorithm computes an approximate CCA to the original pair of matrices with provable guarantees, while requiring asymptotically less operations than the state-of-the-art exact algorithms.",

author = "Haim Avron and Christos Boutsidis and Sivan Toledo and Anastasios Zouzias",

year = "2013",

language = "אנגלית",

pages = "347--355",

note = "null ; Conference date: 16-06-2013 Through 21-06-2013",

}

TY - CONF

T1 - Efficient dimensionality reduction for canonical correlation analysis

AU - Avron, Haim

AU - Boutsidis, Christos

AU - Toledo, Sivan

AU - Zouzias, Anastasios

PY - 2013

Y1 - 2013

N2 - We present a fast algorithm for approximate Canonical Correlation Analysis (CCA). Given a pair of tall-and-thin matrices, the proposed algorithm first employs a randomized dimensionality reduction transform to reduce the size of the input matrices, and then applies any standard CCA algorithm to the new pair of matrices. The algorithm computes an approximate CCA to the original pair of matrices with provable guarantees, while requiring asymptotically less operations than the state-of-the-art exact algorithms.

AB - We present a fast algorithm for approximate Canonical Correlation Analysis (CCA). Given a pair of tall-and-thin matrices, the proposed algorithm first employs a randomized dimensionality reduction transform to reduce the size of the input matrices, and then applies any standard CCA algorithm to the new pair of matrices. The algorithm computes an approximate CCA to the original pair of matrices with provable guarantees, while requiring asymptotically less operations than the state-of-the-art exact algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84897484728&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:84897484728

SP - 347

EP - 355

Y2 - 16 June 2013 through 21 June 2013

ER -

Efficient dimensionality reduction for canonical correlation analysis

Abstract

Conference

Other files and links

Fingerprint

Cite this