Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks

Paul Rodriguez

doi:10.1109/ACSSC.2016.7869190

Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks

Paul Rodriguez

Sección de Electricidad y Electrónica

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

3 Scopus citations

Abstract

Learn 2D filter banks are currently being used in high-impact applications such convolutional neural networks, convolutional sparse representations, etc. However such filter banks usually have plentiful filters, each being non-separable, accounting for a large portion of the overall computational cost. In this paper we propose a novel and computationally appealing alternating optimization based algorithm to estimate a linear combination of separable (rank-1) filters to approximate 2D filter banks. Our computational results show that the proposed method can be faster than (state-of-the-art) tensor Canonical Polyadic decomposition (CPD) method to obtain an approximation of comparable accuracy.

Original language	English
Title of host publication	Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	954-958
Number of pages	5
ISBN (Electronic)	9781538639542
DOIs	https://doi.org/10.1109/ACSSC.2016.7869190
State	Published - 1 Mar 2017
Event	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States Duration: 6 Nov 2016 → 9 Nov 2016

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Conference

Conference	50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
Country/Territory	United States
City	Pacific Grove
Period	6/11/16 → 9/11/16

Keywords

Separable filters
alternating optimization
tensor CPD

Access to Document

10.1109/ACSSC.2016.7869190

Cite this

Rodriguez, P. (2017). Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 954-958). Article 7869190 (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869190

Rodriguez, Paul. / Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. editor / Michael B. Matthews. IEEE Computer Society, 2017. pp. 954-958 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{e63f9f6bfbc14272851e9c5bc40e06b5,

title = "Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks",

abstract = "Learn 2D filter banks are currently being used in high-impact applications such convolutional neural networks, convolutional sparse representations, etc. However such filter banks usually have plentiful filters, each being non-separable, accounting for a large portion of the overall computational cost. In this paper we propose a novel and computationally appealing alternating optimization based algorithm to estimate a linear combination of separable (rank-1) filters to approximate 2D filter banks. Our computational results show that the proposed method can be faster than (state-of-the-art) tensor Canonical Polyadic decomposition (CPD) method to obtain an approximation of comparable accuracy.",

keywords = "Separable filters, alternating optimization, tensor CPD",

author = "Paul Rodriguez",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 ; Conference date: 06-11-2016 Through 09-11-2016",

year = "2017",

month = mar,

day = "1",

doi = "10.1109/ACSSC.2016.7869190",

language = "English",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "954--958",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

Rodriguez, P 2017, Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869190, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 954-958, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 6/11/16. https://doi.org/10.1109/ACSSC.2016.7869190

Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks. / Rodriguez, Paul.
Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 954-958 7869190 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

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

TY - GEN

T1 - Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks

AU - Rodriguez, Paul

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Learn 2D filter banks are currently being used in high-impact applications such convolutional neural networks, convolutional sparse representations, etc. However such filter banks usually have plentiful filters, each being non-separable, accounting for a large portion of the overall computational cost. In this paper we propose a novel and computationally appealing alternating optimization based algorithm to estimate a linear combination of separable (rank-1) filters to approximate 2D filter banks. Our computational results show that the proposed method can be faster than (state-of-the-art) tensor Canonical Polyadic decomposition (CPD) method to obtain an approximation of comparable accuracy.

AB - Learn 2D filter banks are currently being used in high-impact applications such convolutional neural networks, convolutional sparse representations, etc. However such filter banks usually have plentiful filters, each being non-separable, accounting for a large portion of the overall computational cost. In this paper we propose a novel and computationally appealing alternating optimization based algorithm to estimate a linear combination of separable (rank-1) filters to approximate 2D filter banks. Our computational results show that the proposed method can be faster than (state-of-the-art) tensor Canonical Polyadic decomposition (CPD) method to obtain an approximation of comparable accuracy.

KW - Separable filters

KW - alternating optimization

KW - tensor CPD

UR - http://www.scopus.com/inward/record.url?scp=85016259732&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869190

DO - 10.1109/ACSSC.2016.7869190

M3 - Conference contribution

AN - SCOPUS:85016259732

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 954

EP - 958

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

Y2 - 6 November 2016 through 9 November 2016

ER -

Rodriguez P. Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 954-958. 7869190. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2016.7869190

Alternating optimization low-rank expansion algorithm to estimate a linear combination of separable filters to approximate 2D filter banks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this