The Community for Technology Leaders
Subscribe
Issue No.12 - December (2011 vol.33)
pp: 2549-2554
Pedro F. Felzenszwalb , University of Chicago, Chicago
Julian J. McAuley , Australian National University/NICTA, Canberra
ABSTRACT
The MAP inference problem in many graphical models can be solved efficiently using a fast algorithm for computing min-sum products of n \times n matrices. The class of models in question includes cyclic and skip-chain models that arise in many applications. Although the worst-case complexity of the min-sum product operation is not known to be much better than O(n^3), an O(n^{2.5}) expected time algorithm was recently given, subject to some constraints on the input matrices. In this paper, we give an algorithm that runs in O(n^2 \log n) expected time, assuming that the entries in the input matrices are independent samples from a uniform distribution. We also show that two variants of our algorithm are quite fast for inputs that arise in several applications. This leads to significant performance gains over previous methods in applications within computer vision and natural language processing.
INDEX TERMS
Graphical models, MAP inference, min-sum matrix product.
CITATION
Pedro F. Felzenszwalb, Julian J. McAuley, "Fast Inference with Min-Sum Matrix Product", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 12, pp. 2549-2554, December 2011, doi:10.1109/TPAMI.2011.121
REFERENCES
 [1] A.V. Aho, J.E. Hopcroft, and J.D. Ullman, The Design and Analysis of Computer Algorithms. Addison-Wesley, 1974. [2] S.M. Aji and R.J. McEliece, "The Generalized Distributive Law," IEEE Trans. Information Theory, vol. 46, no. 2, pp. 325-343, Mar. 2000. [3] A. Amini, T. Weymouth, and R. Jain, "Using Dynamic Programming for Solving Variational Problems in Vision," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 9, pp. 855-867, Sept. 1990. [4] Y. Amit and A. Kong, "Graphical Templates for Model Registration," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 3, pp. 225-236, Mar. 1996. [5] U. Bertele and F. Brioschi, Nonserial Dynamic Programming. Academic Press, 1972. [6] Y. Boykov and M.-P. Jolly, "Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images," Proc. IEEE Int'l Conf. Computer Vision, 2001. [7] Y. Boykov, O. Veksler, and R. Zabih, "Fast Approximate Energy Minimization via Graph Cuts," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001. [8] T.M. Chan, "More Algorithms for All-Pairs Shortest Paths in Weighted Graphs," Proc. Ann. ACM Symp. Theory of Computing, pp. 590-598, 2007. [9] J.M. Coughlan and S.J. Ferreira, "Finding Deformable Shapes Using Loopy Belief Propagation," Proc. European Conf. Computer Vision, 2002. [10] P.F. Felzenszwalb and D. McAllester, "The Generalized A* Architecture," J. Artificial Intelligence Research, vol. 29, pp. 153-190, 2007. [11] A.M. Frieze and G.R. Grimmett, "The Shortest-Path Problem for Graphs with Random Arc-Lengths," Discrete Applied Math., vol. 10, no. 1, pp. 57-77, 1985. [12] D.R. Karger, D. Koller, and S.J. Phillips, "Finding the Hidden Path: Time Bounds for All-Pairs Shortest Paths," SIAM J. Computing, vol. 22, no. 6, pp. 1199-1217, 1993. [13] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active Contour Models," Int'l J. Computer Vision, vol. 1, no. 4, pp. 321-331, 1987. [14] D. Knuth, "A Generalization of Dijkstra's Algorithm," Information Processing Letters, vol. 6, no. 1, pp. 1-5, 1977. [15] J.J. McAuley and T.S. Caetano, "Exploiting within-Clique Factorizations in Junction-Tree Algorithms," Proc. AI and Statistics, 2010. [16] J.J. McAuley, T.S. Caetano, and M.S. Barbosa, "Graph Rigidity, Cyclic Belief Propagation and Point Pattern Matching," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 11, pp. 2047-2054, Nov. 2008. [17] A. Moffat and T. Takaoka, "An All Pairs Shortest Path Algorithm with Expected Time $O(n^2\log n)$ ," SIAM J. Computing, vol. 16, no. 6, pp. 1023-1031, 1987. [18] M.A. Paskin, "Thin Junction Tree Filters for Simultaneous Localization and Mapping," Proc. Int'l Joint Conf. Artificial Intelligence, 2003. [19] U. Quasthoff, M. Richter, and C. Biemann, "Corpus Portal for Search in Monolingual Corpora," Proc. Language Resources and Evaluation, 2006. [20] L. Sigal and M.J. Black, "Predicting 3D People from 2D Pictures," Proc. Conf. Articulated Motion and Deformable Objects, 2006. [21] V. Strassen, "Gaussian Elimination Is Not Optimal," Numerische Mathematik, vol. 14, no. 3, pp. 354-356, 1969. [22] C. Sutton and A. McCallum, "An Introduction to Conditional Random Fields for Relational Learning," Introduction to Statistical Relational Learning, L. Getoor and B. Taskar, eds., MIT Press, 2006. [23] L.G. Valiant, "General Context-Free Recognition in Less than Cubic Time," J. Computer and System Sciences, vol. 10, pp. 308-315, 1975. [24] J.S. Yedidia, W.T. Freeman, and Y. Weiss, "Generalized Belief Propagation," Proc. Neural Information Processing Systems, 2000.