Stochastic gradient algorithm based on an improved higher order exponentiated error cost function

Umair Bin Mansoor; Syed Muhammad Asad; Azzedine Zerguine

doi:10.1109/ACSSC.2014.7094582

Stochastic gradient algorithm based on an improved higher order exponentiated error cost function

Umair Bin Mansoor
, Syed Muhammad Asad
, Azzedine Zerguine

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

4 Scopus citations

Abstract

We propose stochastic gradient algorithm based on exponentiated cost functions that employ higher order moments of the chosen error. Recently, such algorithms based on exponential dependence of squared of the error have attracted a lot of attention. It has been felt that such algorithms have only been tested in the Gaussian noise environment. Motivated by the performance of the least-mean-fourth algorithm in sub-Gaussian environments, we make use of the same strategy to come up with a new algorithm with superior convergence and steady-state performance. Simulations show promising results.

Original language	English
Title of host publication	Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	900-903
Number of pages	4
ISBN (Electronic)	9781479982974
DOIs	https://doi.org/10.1109/ACSSC.2014.7094582
State	Published - 24 Apr 2015
Event	48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 - Pacific Grove, United States Duration: 2 Nov 2014 → 5 Nov 2014

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2015-April
ISSN (Print)	1058-6393
ISSN (Electronic)	2576-2303

Conference

Conference	48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014
Country/Territory	United States
City	Pacific Grove
Period	2/11/14 → 5/11/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/ACSSC.2014.7094582

Cite this

Bin Mansoor, U., Asad, S. M., & Zerguine, A. (2015). Stochastic gradient algorithm based on an improved higher order exponentiated error cost function. In M. B. Matthews (Ed.), Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 (pp. 900-903). Article 7094582 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2015-April). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2014.7094582

Bin Mansoor, Umair ; Asad, Syed Muhammad ; Zerguine, Azzedine. / Stochastic gradient algorithm based on an improved higher order exponentiated error cost function. Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. editor / Michael B. Matthews. IEEE Computer Society, 2015. pp. 900-903 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

@inproceedings{e48aa042a13d40c2b810ba233a1c663d,

title = "Stochastic gradient algorithm based on an improved higher order exponentiated error cost function",

abstract = "We propose stochastic gradient algorithm based on exponentiated cost functions that employ higher order moments of the chosen error. Recently, such algorithms based on exponential dependence of squared of the error have attracted a lot of attention. It has been felt that such algorithms have only been tested in the Gaussian noise environment. Motivated by the performance of the least-mean-fourth algorithm in sub-Gaussian environments, we make use of the same strategy to come up with a new algorithm with superior convergence and steady-state performance. Simulations show promising results.",

author = "\{Bin Mansoor\}, Umair and Asad, \{Syed Muhammad\} and Azzedine Zerguine",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014 ; Conference date: 02-11-2014 Through 05-11-2014",

year = "2015",

month = apr,

day = "24",

doi = "10.1109/ACSSC.2014.7094582",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "900--903",

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

booktitle = "Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014",

address = "United States",

}

Bin Mansoor, U, Asad, SM & Zerguine, A 2015, Stochastic gradient algorithm based on an improved higher order exponentiated error cost function. in MB Matthews (ed.), Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014., 7094582, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2015-April, IEEE Computer Society, pp. 900-903, 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014, Pacific Grove, United States, 2/11/14. https://doi.org/10.1109/ACSSC.2014.7094582

Stochastic gradient algorithm based on an improved higher order exponentiated error cost function. / Bin Mansoor, Umair; Asad, Syed Muhammad; Zerguine, Azzedine.
Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. ed. / Michael B. Matthews. IEEE Computer Society, 2015. p. 900-903 7094582 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2015-April).

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

TY - GEN

T1 - Stochastic gradient algorithm based on an improved higher order exponentiated error cost function

AU - Bin Mansoor, Umair

AU - Asad, Syed Muhammad

AU - Zerguine, Azzedine

PY - 2015/4/24

Y1 - 2015/4/24

N2 - We propose stochastic gradient algorithm based on exponentiated cost functions that employ higher order moments of the chosen error. Recently, such algorithms based on exponential dependence of squared of the error have attracted a lot of attention. It has been felt that such algorithms have only been tested in the Gaussian noise environment. Motivated by the performance of the least-mean-fourth algorithm in sub-Gaussian environments, we make use of the same strategy to come up with a new algorithm with superior convergence and steady-state performance. Simulations show promising results.

AB - We propose stochastic gradient algorithm based on exponentiated cost functions that employ higher order moments of the chosen error. Recently, such algorithms based on exponential dependence of squared of the error have attracted a lot of attention. It has been felt that such algorithms have only been tested in the Gaussian noise environment. Motivated by the performance of the least-mean-fourth algorithm in sub-Gaussian environments, we make use of the same strategy to come up with a new algorithm with superior convergence and steady-state performance. Simulations show promising results.

UR - https://www.scopus.com/pages/publications/84940561940

U2 - 10.1109/ACSSC.2014.7094582

DO - 10.1109/ACSSC.2014.7094582

M3 - Conference contribution

AN - SCOPUS:84940561940

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

SP - 900

EP - 903

BT - Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014

Y2 - 2 November 2014 through 5 November 2014

ER -

Bin Mansoor U, Asad SM, Zerguine A. Stochastic gradient algorithm based on an improved higher order exponentiated error cost function. In Matthews MB, editor, Conference Record of the 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2014. IEEE Computer Society. 2015. p. 900-903. 7094582. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/ACSSC.2014.7094582

Stochastic gradient algorithm based on an improved higher order exponentiated error cost function

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this