On the Uniqueness of Loopy Belief Propagation Fixed Points

@article{Heskes2004OnTU,
  title={On the Uniqueness of Loopy Belief Propagation Fixed Points},
  author={Tom Heskes},
  journal={Neural Computation},
  year={2004},
  volume={16},
  pages={2379-2413}
}
We derive sufficient conditions for the uniqueness of loopy belief propagation fixed points. These conditions depend on both the structure of the graph and the strength of the potentials and naturally extend those for convexity of the Bethe free energy. We compare them with (a strengthened version of) conditions derived elsewhere for pairwise potentials. We discuss possible implications for convergent algorithms, as well as for other approximate free energies. 
Highly Influential
This paper has highly influenced 16 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 153 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 106 extracted citations

Segmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2009
View 3 Excerpts
Highly Influenced

Loopy Belief Propagation: Convergence and Effects of Message Errors

Journal of Machine Learning Research • 2005
View 10 Excerpts
Highly Influenced

153 Citations

01020'06'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 153 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Belief propagation and statistical physics

P. Pakzad, V. Anantharam
Conference on Information Sciences and Systems • 2002
View 6 Excerpts
Highly Influenced

Introduction to Linear and Nonlinear Programming

Wiley Encyclopedia of Computer Science and Engineering • 1973
View 5 Excerpts
Highly Influenced

A new class of upper bounds on the log partition function

IEEE Transactions on Information Theory • 2002
View 3 Excerpts
Highly Influenced

Approximate inference in Boltzmann machines

Artif. Intell. • 2003
View 2 Excerpts
Highly Influenced

Belief Propagation on Partially Ordered Sets

Mathematical Systems Theory in Biology, Communications, Computation, and Finance • 2003
View 3 Excerpts
Highly Influenced

Correctness of belief propagation in graphical models with arbitrary topology

Y. Weiss, W. Freeman
Neural Computation, • 2001
View 2 Excerpts

Similar Papers

Loading similar papers…