The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.09 - Sept. (2013 vol.35)
pp: 2304-2306
B. Flach , Fac. of Electr. Eng., Czech Tech. Univ., Prague, Czech Republic
ABSTRACT
The aim of this short note is to draw attention to a method by which the partition function and marginal probabilities for a certain class of random fields on complete graphs can be computed in polynomial time. This class includes Ising models with homogeneous pairwise potentials but arbitrary (inhomogeneous) unary potentials. Similarly, the partition function and marginal probabilities can be computed in polynomial time for random fields on complete bipartite graphs, provided they have homogeneous pairwise potentials. We expect that these tractable classes of large-scale random fields can be very useful for the evaluation of approximation algorithms by providing exact error estimates.
INDEX TERMS
Labeling, Computational modeling, Bipartite graph, Partitioning algorithms, Time complexity, Approximation methods, Polynomials,Markov random fields,
CITATION
B. Flach, "A Class of Random Fields on Complete Graphs with Tractable Partition Function", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.35, no. 9, pp. 2304-2306, Sept. 2013, doi:10.1109/TPAMI.2013.99
REFERENCES
[1] A.A. Bulatov and M. Grohe, "The Complexity of Partition Functions," Theoretical Computer Science, vol. 348, nos. 2/3, pp. 148-186, 2005.
[2] M.J. Wainwright, T. Jaakkola, and A.S. Willsky, "A New Class of Upper Bounds on the Log Partition Function," IEEE Trans. Information Theory, vol. 51, no. 7, pp. 2313-2335, July 2005.
[3] M. Wainwright and M. Jordan, "Log-Determinant Relaxation for Approximate Inference in Discrete Markov Random Fields," IEEE Trans. Signal Processing, vol. 54, no. 6, pp. 2099-2109, http://dx.doi.org/10.1109TSP. 2006.874409 , June 2006.
[4] D. Sontag and T. Jaakkola, "New Outer Bounds on the Marginal Polytope," Proc. Neural Information Processing System, J.C. Platt, D. Koller, Y. Singer, and S.T. Roweis, eds., 2007.
[5] T. Hazan and A. Shashua, "Norm-Product Belief Propagation: Primal-Dual Message-Passing for Approximate Inference," IEEE Trans. Information Theory, vol. 56, no. 12, pp. 6294-6316, Dec. 2010.
[6] F. Korč, V. Kolmogorov, and C.H. Lampert, "Approximating Marginals Using Discrete Energy Minimization," Proc. Workshop Inferning: Interactions between Inference and Learning, 2012.
[7] N.N. Schraudolph and D. Kamenetsky, "Efficient Exact Inference in Planar Ising Models," Proc. Neural Information Processing System, pp. 1417-1424, 2009.
107 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool