Probabilistic low-rank subspace clustering

S. Derin Babacan, Shinichi Nakajima, Minh N. Do

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we consider the problem of clustering data points into lowdimensional subspaces in the presence of outliers. We pose the problem using a density estimation formulation with an associated generative model. Based on this probability model, we first develop an iterative expectation-maximization (EM) algorithm and then derive its global solution. In addition, we develop two Bayesian methods based on variational Bayesian (VB) approximation, which are capable of automatic dimensionality selection. While the first method is based on an alternating optimization scheme for all unknowns, the second method makes use of recent results in VB matrix factorization leading to fast and effective estimation. Both methods are extended to handle sparse outliers for robustness and can handle missing values. Experimental results suggest that proposed methods are very effective in subspace clustering and identifying outliers.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 25
Subtitle of host publication26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Pages2744-2752
Number of pages9
StatePublished - Dec 1 2012
Event26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 - Lake Tahoe, NV, United States
Duration: Dec 3 2012Dec 6 2012

Publication series

NameAdvances in Neural Information Processing Systems
Volume4
ISSN (Print)1049-5258

Other

Other26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
CountryUnited States
CityLake Tahoe, NV
Period12/3/1212/6/12

Fingerprint

Factorization

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Babacan, S. D., Nakajima, S., & Do, M. N. (2012). Probabilistic low-rank subspace clustering. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 (pp. 2744-2752). (Advances in Neural Information Processing Systems; Vol. 4).

Probabilistic low-rank subspace clustering. / Babacan, S. Derin; Nakajima, Shinichi; Do, Minh N.

Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012. 2012. p. 2744-2752 (Advances in Neural Information Processing Systems; Vol. 4).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Babacan, SD, Nakajima, S & Do, MN 2012, Probabilistic low-rank subspace clustering. in Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012. Advances in Neural Information Processing Systems, vol. 4, pp. 2744-2752, 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012, Lake Tahoe, NV, United States, 12/3/12.
Babacan SD, Nakajima S, Do MN. Probabilistic low-rank subspace clustering. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012. 2012. p. 2744-2752. (Advances in Neural Information Processing Systems).
Babacan, S. Derin ; Nakajima, Shinichi ; Do, Minh N. / Probabilistic low-rank subspace clustering. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012. 2012. pp. 2744-2752 (Advances in Neural Information Processing Systems).
@inproceedings{7545ac54c4a346579bb95180ba91b03d,
title = "Probabilistic low-rank subspace clustering",
abstract = "In this paper, we consider the problem of clustering data points into lowdimensional subspaces in the presence of outliers. We pose the problem using a density estimation formulation with an associated generative model. Based on this probability model, we first develop an iterative expectation-maximization (EM) algorithm and then derive its global solution. In addition, we develop two Bayesian methods based on variational Bayesian (VB) approximation, which are capable of automatic dimensionality selection. While the first method is based on an alternating optimization scheme for all unknowns, the second method makes use of recent results in VB matrix factorization leading to fast and effective estimation. Both methods are extended to handle sparse outliers for robustness and can handle missing values. Experimental results suggest that proposed methods are very effective in subspace clustering and identifying outliers.",
author = "Babacan, {S. Derin} and Shinichi Nakajima and Do, {Minh N.}",
year = "2012",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781627480031",
series = "Advances in Neural Information Processing Systems",
pages = "2744--2752",
booktitle = "Advances in Neural Information Processing Systems 25",

}

TY - GEN

T1 - Probabilistic low-rank subspace clustering

AU - Babacan, S. Derin

AU - Nakajima, Shinichi

AU - Do, Minh N.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this paper, we consider the problem of clustering data points into lowdimensional subspaces in the presence of outliers. We pose the problem using a density estimation formulation with an associated generative model. Based on this probability model, we first develop an iterative expectation-maximization (EM) algorithm and then derive its global solution. In addition, we develop two Bayesian methods based on variational Bayesian (VB) approximation, which are capable of automatic dimensionality selection. While the first method is based on an alternating optimization scheme for all unknowns, the second method makes use of recent results in VB matrix factorization leading to fast and effective estimation. Both methods are extended to handle sparse outliers for robustness and can handle missing values. Experimental results suggest that proposed methods are very effective in subspace clustering and identifying outliers.

AB - In this paper, we consider the problem of clustering data points into lowdimensional subspaces in the presence of outliers. We pose the problem using a density estimation formulation with an associated generative model. Based on this probability model, we first develop an iterative expectation-maximization (EM) algorithm and then derive its global solution. In addition, we develop two Bayesian methods based on variational Bayesian (VB) approximation, which are capable of automatic dimensionality selection. While the first method is based on an alternating optimization scheme for all unknowns, the second method makes use of recent results in VB matrix factorization leading to fast and effective estimation. Both methods are extended to handle sparse outliers for robustness and can handle missing values. Experimental results suggest that proposed methods are very effective in subspace clustering and identifying outliers.

UR - http://www.scopus.com/inward/record.url?scp=84877735016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877735016&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84877735016

SN - 9781627480031

T3 - Advances in Neural Information Processing Systems

SP - 2744

EP - 2752

BT - Advances in Neural Information Processing Systems 25

ER -