Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering

Jacob Goldberger; Yaniv Opochinsky

doi:10.1109/ICASSP.2019.8683613

Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering

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

Abstract

The information-bottleneck (IB) principle is defined in terms of mutual information. This study defines mutual information between two random variables using the Jensen-Shannon (JS) divergence instead of the standard definition which is based on the Kullback-Leibler (KL) divergence. We reformulate the information-bottleneck principle using the proposed mutual information and apply it to the problem of pairwise clustering. We show that applying IB to clustering tasks using JS divergences instead of KL yields improved results. This indicates that JS-based mutual information has an expressive power at least as the standard KL-based mutual information.

Original language	English
Title of host publication	2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3507-3511
Number of pages	5
ISBN (Electronic)	9781479981311
DOIs	https://doi.org/10.1109/ICASSP.2019.8683613
State	Published - May 2019
Event	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom Duration: 12 May 2019 → 17 May 2019

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2019-May
ISSN (Print)	1520-6149

Conference

Conference	44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Country/Territory	United Kingdom
City	Brighton
Period	12/05/19 → 17/05/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Jensen-Shannon (JS) divergence
information bottleneck
pairwise clustering

Access to Document

10.1109/ICASSP.2019.8683613

Cite this

Goldberger, J., & Opochinsky, Y. (2019). Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 3507-3511). Article 8683613 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8683613

Goldberger, Jacob ; Opochinsky, Yaniv. / Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3507-3511 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{8471d10dae9f482080afff95e6cf11fe,

title = "Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering",

abstract = "The information-bottleneck (IB) principle is defined in terms of mutual information. This study defines mutual information between two random variables using the Jensen-Shannon (JS) divergence instead of the standard definition which is based on the Kullback-Leibler (KL) divergence. We reformulate the information-bottleneck principle using the proposed mutual information and apply it to the problem of pairwise clustering. We show that applying IB to clustering tasks using JS divergences instead of KL yields improved results. This indicates that JS-based mutual information has an expressive power at least as the standard KL-based mutual information.",

keywords = "Jensen-Shannon (JS) divergence, information bottleneck, pairwise clustering",

author = "Jacob Goldberger and Yaniv Opochinsky",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",

year = "2019",

month = may,

doi = "10.1109/ICASSP.2019.8683613",

language = "אנגלית",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3507--3511",

booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

address = "ארצות הברית",

}

Goldberger, J & Opochinsky, Y 2019, Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683613, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 3507-3511, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8683613

Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering. / Goldberger, Jacob; Opochinsky, Yaniv.
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3507-3511 8683613 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

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

TY - GEN

T1 - Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering

AU - Goldberger, Jacob

AU - Opochinsky, Yaniv

PY - 2019/5

Y1 - 2019/5

N2 - The information-bottleneck (IB) principle is defined in terms of mutual information. This study defines mutual information between two random variables using the Jensen-Shannon (JS) divergence instead of the standard definition which is based on the Kullback-Leibler (KL) divergence. We reformulate the information-bottleneck principle using the proposed mutual information and apply it to the problem of pairwise clustering. We show that applying IB to clustering tasks using JS divergences instead of KL yields improved results. This indicates that JS-based mutual information has an expressive power at least as the standard KL-based mutual information.

AB - The information-bottleneck (IB) principle is defined in terms of mutual information. This study defines mutual information between two random variables using the Jensen-Shannon (JS) divergence instead of the standard definition which is based on the Kullback-Leibler (KL) divergence. We reformulate the information-bottleneck principle using the proposed mutual information and apply it to the problem of pairwise clustering. We show that applying IB to clustering tasks using JS divergences instead of KL yields improved results. This indicates that JS-based mutual information has an expressive power at least as the standard KL-based mutual information.

KW - Jensen-Shannon (JS) divergence

KW - information bottleneck

KW - pairwise clustering

UR - http://www.scopus.com/inward/record.url?scp=85068986419&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8683613

DO - 10.1109/ICASSP.2019.8683613

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85068986419

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 3507

EP - 3511

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019

Y2 - 12 May 2019 through 17 May 2019

ER -

Goldberger J, Opochinsky Y. Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3507-3511. 8683613. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2019.8683613

Information-bottleneck Based on the Jensen-shannon Divergence with Applications to Pairwise Clustering

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this