Abstract
Recent work (Yedidia, Freeman, Weiss [22]) has shown that stable points of belief propagation (BP) algorithms [12] for graphs with loops correspond to extrema of the Bethe free energy [3]. These BP algorithms have been used to obtain good solutions to problems for which alternative algorithms fail to work [4], [5], [10] [11]. In this paper we introduce a discrete iterative algorithm which we prove is guaranteed to converge to a minimum of the Bethe free energy. We call this the double-loop algorithm because it contains an inner and an outer loop. The algorithm is developed by decomposing the free energy into a convex part and a concave part, see [25], and extends a class of mean field theory algorithms developed by [7],[8] and, in particular, [13]. Moreover, the double-loop algorithm is formally very similar to BP which may help understand when BP converges. In related work [24] we extend this work to the more general Kikuchi approximation [3] which includes the Bethe free energy as a special case. It is anticipated that these double-loop algorithms will be useful for solving optimization problems in computer vision and other applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
S. Amari. “Differential Geometry of curved exponential families — Curvature and information loss. Annals of Statistics, vol. 10, no. 2, pp 357–385. 1982.
M. Arbib (Ed.) The Handbook of Brain Theory and Neural Networks. A Bradford Book. The MIT Press. 1995.
C. Domb and M.S. Green (Eds). Phase Transitions and Critical Phenomena. Vol. 2. Academic Press. London. 1972.
W.T. Freeman and E.C. Pasztor. “Learning low level vision”. In Proc. International Conference of Computer Vision. ICCV’99. pp 1182–1189. 1999.
B. Frey. Graphical Models for Pattern Classification, Data Compression and Channel Coding. MIT Press. 1998.
S. Kirkpatrick, C. Gelatt (Jr.), and M. Vecchi. “Optimization by Simulated Annealing”. Science, 220:671–680. 1983.
J. Kosowsky and A.L. Yuille. “The Invisible Hand Algorithm: Solving the Assignment Problem with Statistical Physics”. Neural Networks., Vol. 7, No. 3, pp 477–490. 1994.
J. Kosowsky. Flows Suspending Iterative Algorithms. PhD Thesis. Division of Applied Sciences. Harvard University. Cambridge, Massachusetts. 1995.
C.M. Marcus and R.M. Westervelt. “Dynamics of iterated-map neural networks”. Physical Review A, 40, pp 501–504. 1989.
R.J. McEliece, D.J.C. Mackay, and J.F. Cheng. “Turbo decoding as an instance of Pearl’s belief propagation algorithm”. IEEE Journal on Selected Areas in Communication. 16(2), pp 140–152. 1998.
K.P. Murphy, Y. Weiss, and M.I. Jordan. “Loopy belief propagation for approximate inference: an empirical study”. In Proceedings of Uncertainty in AI. 1999.
J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann. 1988.
A. Rangarajan, S. Gold, and E. Mjolsness. “A Novel Optimizing Network Architecture with Applications”. Neural Computation, 8(5), pp 1041–1060. 1996.
A. Rangarajan, A.L. Yuille, S. Gold. and E. Mjolsness.” A Convergence Proof for the Softassign Quadratic assignment Problem”. In Proceedings of NIPS’96. Snowmass. Colorado. 1996.
B.D. Ripley. “Pattern Recognition and Neural Networks”. Cambridge University Press. 1996.
L. K. Saul, T. Jaakkola, and M. I. Jordan. “Mean Field Theory for Sigmoid Belief Networks”. Journal of Artificial Intelligence Research, 4, 61–76, 1996.
R. Sinkhorn. “A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices”. Ann. Math. Statist.. 35, pp 876–879. 1964.
G. Strang. Introduction to Applied Mathematics. Wellesley-Cambridge Press. Wellesley, Massachusetts. 1986.
F.R. Waugh and R.M. Westervelt. “Analog neural networks with local competition: I. Dynamics and stability”. Physical Review E, 47(6), pp 4524–4536. 1993.
Y. Weiss. “Correctness of local probability propagation in graphical models with loops”. Neural Computation 12 (1–41) 2000.
Y. Weiss. “Comparing the mean field method and belief propagation for approximate inference in MRFs”. To appear in Advanced Mean Field Methods. Saad and Opper (Eds). MIT Press. 2001.
J.S. Yedidia, W.T. Freeman, Y. Weiss. “Bethe free energy, Kikuchi approximations and belief propagation algorithms”. To appear in NIPS’2000. 2000.
A.L. Yuille and J.J. Kosowsky. “Statistical Physics Algorithms that Converge”. Neural Computation. 6, pp 341–356. 1994.
A.L. Yuille. “A Double-Loop Algorithm to Minimize the Bethe and Kikuchi Free Energies”. Submitted to Neural Computation. 2001.
A.L. Yuille and A. Rangarajan. “The Concave-Convex Procedure (CCCP)”. Submitted to Neural Computation. 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yuille, A. (2001). A Double-Loop Algorithm to Minimize the Bethe Free Energy. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2001. Lecture Notes in Computer Science, vol 2134. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44745-8_1
Download citation
DOI: https://doi.org/10.1007/3-540-44745-8_1
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42523-6
Online ISBN: 978-3-540-44745-0
eBook Packages: Springer Book Archive