Random Diffusion Representations

Moshe Salhov; Amir Averbuch

doi:10.1109/SampTA45681.2019.9030852

Random Diffusion Representations

Moshe Salhov, Amir Averbuch

School of Computer Science

Tel Aviv University

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

Abstract

The diffusion maps is a kernel based method for manifold learning and data analysis that models a Markovian process over data. Analysis of this process provides meaningful information about the inner geometric structures in the data.In this paper, we present a representation framework for analyzing datasets. This framework is based on a random approximation of the diffusion maps kernel. The resulted representation approximate the pair-wise diffusion distance, does not depend on the data size and it is invariant to scale.

Original language	English
Title of host publication	2019 13th International Conference on Sampling Theory and Applications, SampTA 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728137414
DOIs	https://doi.org/10.1109/SampTA45681.2019.9030852
State	Published - Jul 2019
Event	13th International Conference on Sampling Theory and Applications, SampTA 2019 - Bordeaux, France Duration: 8 Jul 2019 → 12 Jul 2019

Publication series

Name	2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

Conference

Conference	13th International Conference on Sampling Theory and Applications, SampTA 2019
Country/Territory	France
City	Bordeaux
Period	8/07/19 → 12/07/19

Funding

Funders	Funder number
Blavatnik Computer Science Research Fund
INdo-ISrael CollAborative for Infrastructure Security
Israel Ministry of Science and Technology	3-14481
Israel Science Foundation	1556/17

Access to Document

10.1109/SampTA45681.2019.9030852

Cite this

@inproceedings{479ffd31f0ab4c67bb2d0809ce652af1,

title = "Random Diffusion Representations",

abstract = "The diffusion maps is a kernel based method for manifold learning and data analysis that models a Markovian process over data. Analysis of this process provides meaningful information about the inner geometric structures in the data.In this paper, we present a representation framework for analyzing datasets. This framework is based on a random approximation of the diffusion maps kernel. The resulted representation approximate the pair-wise diffusion distance, does not depend on the data size and it is invariant to scale.",

author = "Moshe Salhov and Amir Averbuch",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 13th International Conference on Sampling Theory and Applications, SampTA 2019 ; Conference date: 08-07-2019 Through 12-07-2019",

year = "2019",

month = jul,

doi = "10.1109/SampTA45681.2019.9030852",

language = "אנגלית",

series = "2019 13th International Conference on Sampling Theory and Applications, SampTA 2019",

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

booktitle = "2019 13th International Conference on Sampling Theory and Applications, SampTA 2019",

address = "ארצות הברית",

}

Salhov, M & Averbuch, A 2019, Random Diffusion Representations. in 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019., 9030852, 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019, Institute of Electrical and Electronics Engineers Inc., 13th International Conference on Sampling Theory and Applications, SampTA 2019, Bordeaux, France, 8/07/19. https://doi.org/10.1109/SampTA45681.2019.9030852

Random Diffusion Representations. / Salhov, Moshe; Averbuch, Amir.
2019 13th International Conference on Sampling Theory and Applications, SampTA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9030852 (2019 13th International Conference on Sampling Theory and Applications, SampTA 2019).

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

TY - GEN

T1 - Random Diffusion Representations

AU - Salhov, Moshe

AU - Averbuch, Amir

PY - 2019/7

Y1 - 2019/7

N2 - The diffusion maps is a kernel based method for manifold learning and data analysis that models a Markovian process over data. Analysis of this process provides meaningful information about the inner geometric structures in the data.In this paper, we present a representation framework for analyzing datasets. This framework is based on a random approximation of the diffusion maps kernel. The resulted representation approximate the pair-wise diffusion distance, does not depend on the data size and it is invariant to scale.

AB - The diffusion maps is a kernel based method for manifold learning and data analysis that models a Markovian process over data. Analysis of this process provides meaningful information about the inner geometric structures in the data.In this paper, we present a representation framework for analyzing datasets. This framework is based on a random approximation of the diffusion maps kernel. The resulted representation approximate the pair-wise diffusion distance, does not depend on the data size and it is invariant to scale.

UR - http://www.scopus.com/inward/record.url?scp=85082879844&partnerID=8YFLogxK

U2 - 10.1109/SampTA45681.2019.9030852

DO - 10.1109/SampTA45681.2019.9030852

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

AN - SCOPUS:85082879844

T3 - 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

BT - 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Sampling Theory and Applications, SampTA 2019

Y2 - 8 July 2019 through 12 July 2019

ER -

Random Diffusion Representations

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this