Sampling methods for unsupervised learning

Rob Fergus; Andrew Zisserman; Pietro Perona

Sampling methods for unsupervised learning

Rob Fergus, Andrew Zisserman, Pietro Perona

Computer Science

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

Abstract

We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 17 - Proceedings of the 2004 Conference, NIPS 2004
Publisher	Neural information processing systems foundation
ISBN (Print)	0262195348, 9780262195348
State	Published - 2005
Event	18th Annual Conference on Neural Information Processing Systems, NIPS 2004 - Vancouver, BC, Canada Duration: Dec 13 2004 → Dec 16 2004

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Other

Other	18th Annual Conference on Neural Information Processing Systems, NIPS 2004
Country/Territory	Canada
City	Vancouver, BC
Period	12/13/04 → 12/16/04

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Sampling methods for unsupervised learning. / Fergus, Rob; Zisserman, Andrew; Perona, Pietro.
Advances in Neural Information Processing Systems 17 - Proceedings of the 2004 Conference, NIPS 2004. Neural information processing systems foundation, 2005. (Advances in Neural Information Processing Systems).

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

Fergus, R, Zisserman, A & Perona, P 2005, Sampling methods for unsupervised learning. in Advances in Neural Information Processing Systems 17 - Proceedings of the 2004 Conference, NIPS 2004. Advances in Neural Information Processing Systems, Neural information processing systems foundation, 18th Annual Conference on Neural Information Processing Systems, NIPS 2004, Vancouver, BC, Canada, 12/13/04.

@inproceedings{c73cd15408504dd9b355739463196f08,

title = "Sampling methods for unsupervised learning",

abstract = "We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.",

author = "Rob Fergus and Andrew Zisserman and Pietro Perona",

year = "2005",

language = "English (US)",

isbn = "0262195348",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

booktitle = "Advances in Neural Information Processing Systems 17 - Proceedings of the 2004 Conference, NIPS 2004",

note = "18th Annual Conference on Neural Information Processing Systems, NIPS 2004 ; Conference date: 13-12-2004 Through 16-12-2004",

}

TY - GEN

T1 - Sampling methods for unsupervised learning

AU - Fergus, Rob

AU - Zisserman, Andrew

AU - Perona, Pietro

PY - 2005

Y1 - 2005

N2 - We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.

AB - We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.

UR - http://www.scopus.com/inward/record.url?scp=84898968638&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898968638&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898968638

SN - 0262195348

SN - 9780262195348

T3 - Advances in Neural Information Processing Systems

BT - Advances in Neural Information Processing Systems 17 - Proceedings of the 2004 Conference, NIPS 2004

PB - Neural information processing systems foundation

T2 - 18th Annual Conference on Neural Information Processing Systems, NIPS 2004

Y2 - 13 December 2004 through 16 December 2004

ER -

Sampling methods for unsupervised learning

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this