A Caltech Library Service

Sampling Methods for Unsupervised Learning

Fergus, Rob and Zisserman, Andrew and Perona, Pietro (2005) Sampling Methods for Unsupervised Learning. In: Advances in Neural Information Processing Systems 17 (NIPS 2004). Advances in Neural Information Processing Systems. No.17. MIT Press , Cambridge, MA, pp. 433-440. ISBN 0-262-19534-8.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2005 Massachusetts Institute of Technology. Funding was provided by EC Project CogViSys, EC NOE Pascal, Caltech CNSE, the NSF and the UK EPSRC. Thanks to F. Schaffalitzky & P. Torr for useful discussions.
Funding AgencyGrant Number
European Research Council (ERC)UNSPECIFIED
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Engineering and Physical Sciences Research Council (EPSRC)UNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:17
Record Number:CaltechAUTHORS:20160314-151925758
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:65340
Deposited By: Kristin Buxton
Deposited On:14 Mar 2016 23:52
Last Modified:03 Oct 2019 09:46

Repository Staff Only: item control page