A Caltech Library Service

Statistical physics, mixtures of distributions, and the EM algorithm

Yuille, Alan L. and Stolorz, Paul and Utans, Joachim (1994) Statistical physics, mixtures of distributions, and the EM algorithm. Neural Computation, 6 (2). pp. 334-340. ISSN 0899-7667.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


We show that there are strong relationships between approaches to optmization and learning based on statistical physics or mixtures of experts. In particular, the EM algorithm can be interpreted as converging either to a local maximum of the mixtures model or to a saddle point solution to the statistical physics system. An advantage of the statistical physics approach is that it naturally gives rise to a heuristic continuation method, deterministic annealing, for finding good solutions.

Item Type:Article
Related URLs:
URLURL TypeDescription
Additional Information:© 1994 Massachusetts Institute of Technology. Posted Online April 10, 2008. We would like to thank Eric Mjolsness and Anand Rangarajan for helpful conversations and encouragement. One of us (A.L.Y.) thanks DARPA and the Air Force for support under contract F49620-92-J-0466 and Geoffrey Hinton for a helpful conversation.
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
United States Air ForceF49620-92-J-0466
Issue or Number:2
Record Number:CaltechAUTHORS:YUInc94
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:13652
Deposited By: Jason Perez
Deposited On:18 Jun 2009 18:20
Last Modified:03 Oct 2019 00:42

Repository Staff Only: item control page