A new look at reweighted message passing

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 37, Issue 5, 2015, Pages 919-930

  Kolmogorov, Vladimir ^a  

^a INSTITUTE OF SCIENCE AND TECHNOLOGY AUSTRIA   (Austria)

Author keywords

graphical models; MAP estimation; message passing algorithms

Indexed keywords

FORESTRY; GRAPHIC METHODS;

GRAPHICAL MODEL; HIGHER-ORDER; MAP ESTIMATION; MESSAGE PASSING ALGORITHM; MIN-SUM; REAL-WORLD PROBLEM;

MESSAGE PASSING;

ALGORITHMS; DIFFUSION; MODELS;

EID: 84926429477     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2014.2363465     Document Type: Article

References (38)

1. T. Werner, "A linear programming approach to max-sum problem: A review, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 7, pp. 1165-1179, Jul. 2007.
2. V. Kolmogorov, "Convergent tree-reweighted message passing for energy minimization, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 10, pp. 1568-1583, Oct. 2006.
3. M. Wainwright, T. Jaakkola, and A. Willsky, "MAP estimation via agreement on (hyper)trees: Message-passing and linear-programming approaches, " IEEE Trans. Inf. Theory, vol. 51, no. 11, pp. 3697-3717, Nov. 2005.
4. T. Hazan and A. Shashua, "Norm-product belief propagation: Primal-dual message-passing for approximate inference, " IEEE Trans. Inf. Theory, vol. 56, no. 12, pp. 6294-6316, Dec. 2010.
5. T. Schoenemann and V. Kolmogorov, "Generalized sequential tree-reweighted message passing, " in Advanced Structured Prediction, S. Nowozin, P. V. Gehler, J. Jancsary, and C. Lampert, Eds. Cambridge, MA, USA: MIT Press, 2014, code: https://github. com/Thomas1205/Optimization-Toolbox.
6. T. Werner, "Revisiting the linear programming relaxation approach to Gibbs energy minimization and weighted constraint satisfaction, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 8, pp. 1474-1488, Aug. 2010.
7. A. Globerson and T. Jaakkola, "Fixing max-product: Convergent message passing algorithms for MAP LP-relaxations, " in Proc. Adv. Neural Inf. Process. Syst., 2007, pp. 553-560.
8. D. Sontag, "Approximate inference in graphical models using LP relaxations, " Ph.D. dissertation, Dept. Elect. Eng. Comput. Sci., MIT, Cambridge, MA, USA, 2010.
9. D. Sontag, A. Globerson, and T. Jaakkola, "Introduction to dual decomposition for inference, " in Optimization for Machine Learning, S. Sra, S. Nowozin, and S. Wright, Eds. Cambridge, MA, USA: MIT Press, 2011.
10. M. P. Kumar and P. Torr, "Efficiently solving convex relaxations for MAP estimation, " in Proc. 25th Int. Conf. Mach. Learn., 2008, pp. 680-687.
11. D. Sontag and T. Jaakkola, "Tree block coordinate descent for MAP in graphical models, " in Proc. 12th Int. Conf. Artif. Intell. Stat., 2009, vol. 8, pp. 544-551.
12. T. Meltzer, A. Globerson, and Y. Weiss, "Convergent message passing algorithms-a unifying view, " in Proc. 25th Conf. Uncertainty Artif. Intell., 2009, pp. 393-401.
13. Y. Zheng, P. Chen, and J.-Z. Cao, "MAP-MRF inference based on extended junction tree representation, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2012, pp. 1696-1703.
14. H. Wang and D. Koller, "Subproblem-tree calibration: A unified approach to max-product message passing, " in Proc. Int. Conf. Mach. Learn., 2013, pp. 190-198.
15. G. Storvik and G. Dahl, "Lagrangian-based methods for finding MAP, " IEEE Trans. Image Process., vol. 9, no. 3, pp. 469-479, Mar. 2000.
16. M. I. Schlesinger and V. V. Giginyak, "Solution to structural recognition (MAX, +)-problems by their equivalent transformations, " Control Syst. Comput., vol. 1, pp. 3-15, 2007.
17. N. Komodakis and N. Paragios, "Beyond loose LP-relaxations: Optimizing MRFs by repairing cycles, " in Proc. 10th Eur. Conf. Comput. Vis., 2008, pp. 806-820.
18. N. Komodakis and N. Paragios, "Beyond pairwise energies: Efficient optimization for higher-order MRFs, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 2985-2992.
19. J. Johnson, D. M. Malioutov, and A. S. Willsky, "Lagrangian relaxation for MAP estimation in graphical models, " in Proc. 45th Annu. Allerton Conf. Commun., Control Comput., 2007.
20. P. Ravikumar, A. Agarwal, and M. J. Wainwright, "Messagepassing for graph-structured linear programs: Proximal projections, convergence, and rounding schemes, " J. Mach. Learn. Res., vol. 11, pp. 1043-1080, Mar. 2010.
21. V. Jojic, S. Gould, and D. Koller, "Accelerated dual decomposition for MAP inference, " in Proc. Int. Conf. Mach. Learn., 2010, pp. 503-510.
22. B. Savchynskyy, J. H. Kappes, S. Schmidt, and C. Schnorr, "A study of Nesterov's scheme for Lagrangian decomposition and MAP labeling, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2011, pp. 1817-1823.
23. A. F. T. Martins, M. A. T. Figueiredo, P. M. Q. Aguiar, N. A. Smith, and E. P. Xing, "An augmented Lagrangian approach to constrained MAP inference, " in Proc. 28th Int. Conf. Mach. Learn., 2011, pp. 169-176.
24. O. Meshi and A. Globerson, "An alternating direction method for dual MAP LP relaxation, " in Proc. Eur. Conf. Mach. Learn. knowl. Discovery Databases, 2011, pp. 470-483.
25. S. Schmidt, B. Savchynskyy, J. H. Kappes, and C. Schnorr, "Evaluation of a first-order primal-dual algorithm for MRF energy minimization, " in Proc. Energy Minimization Methods Comput. Vis. Pattern Recognit., 2011, pp. 89-103.
26. T. Pock, D. Cremers, H. Bischof, and A. Chambolle, "An algorithm for minimizing the piecewise smooth Mumford-Shah functional, " in Proc. IEEE 12th Int. Conf. Comput. Vis., 2009, pp. 1133-1140.
27. J. H. Kappes, B. Savchynskyy, and C. Schnorr, "A bundle approach to efficient MAP-inference by Lagrangian relaxation, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2012, pp. 1688-1695.
28. D. V. N. Luong, P. Parpas, D. Rueckert, and B. Rustem, "Solving MRF minimization by mirror descent, " in Proc. Adv. Vis. Comput., 2012, pp. 587-598.
29. B. Savchynskyy, S. Schmidt, J. H. Kappes, and C. Schnorr, "Efficient MRF energy minimization via adaptive diminishing smoothing, " in Proc. 25th Conf. Uncertainty Artif. Intell., 2012, pp. 746-755.
30. J. Thapper and S.-Zivn-y, "The power of linear programming for valued CSPs, " in Proc. 53rd Annu. IEEE Symp. Found. Comput. Sci., 2012, pp. 669-678.
31. V. Kolmogorov, "The power of linear programming for finitevalued CSPs: A constructive characterization, " in Proc. 40th Int. Conf. Automata, Lang., Programm., 2013, pp. 625-636.
32. A. Globerson, D. Sontag, D. K. Choe, and Y. Li. (2012). MPLP code, version 2 [Online]. Availble: http://cs.nyu.edu/~dsontag/code/mplp-ver2.tgz
33. J. Kappes, B. Andres, C. Schnorr, F. Hamprecht, S. Nowozin, D. Batra, J. Lellman, N. Komodakis, S. Kim, B. Kausler, and C. Rother, "A comparative study of modern inference techniques for discrete energy minimization problems, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2013, pp. 1328-1335.
34. (2013). [Online]. Availble: https://web.archive.org/web/http://cs.nyu.edu/~dsontag/code/README-v2.html
35. O. J. Woodford, P. H. S. Torr, I. D. Reid, and A. W. Fitzgibbon, "Global stereo reconstruction under second order smoothness priors, " in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2008, pp. 2115-2128.
36. D. Sontag, T. Meltzer, A. Globerson, Y. Weiss, and T. Jaakkola, "Tightening LP relaxations for MAP using message passing, " in Proc. 24th Conf. Uncertainty Artif. Intell., 2008, pp. 503-510.
37. D. Sontag, D. K. Choe, and Y. Li, "Efficiently searching for frustrated cycles in MAP inference, " in Proc. 25th Conf. Uncertainty Artif. Intell., 2012, pp. 795-804.
38. (2012). [Online]. Availble: http://www.cs.huji.ac.il/project/PASCAL/