Convergent decomposition solvers for tree-reweighted free energies

Journal of Machine Learning Research

Volumn 15, Issue , 2011, Pages 388-398

  Jancsary, Jeremy ^a   Matz, Gerald ^b  

^a AUSTRIAN RESEARCH INSTITUTE FOR ARTIFICIAL INTELLIGENCE   (Austria)

^b VIENNA UNIVERSITY OF TECHNOLOGY   (Austria)

Author keywords

[No Author keywords available]

Indexed keywords

GLOBAL CONVERGENCE; GRAPHICAL MODEL; MARGINAL PROBABILITY; MESSAGE PASSING ALGORITHM; PARTITION FUNCTIONS; PROBLEM DECOMPOSITION; SPANNING TREE; UPPER BOUND;

ALGORITHMS; ARTIFICIAL INTELLIGENCE;

FREE ENERGY;

EID: 84862283435     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (22)

1. J. Barzilai and J. M. Borwein. Two-point step size gradient methods. IMA Journal of Numerical Analysis, 8:141-148, 1988.
2. D. P. Bertsekas. Nonlinear Programming. Athena Scientific, 2nd edition, 1999.
3. E. G. Birgin, J. M. Martinez, and M. Raydan. Nonmonotone spectral projected gradient methods on convex sets. SIAM Journal of Optimization, 10(4): 1196-1211, 2000.
4. R. Byrd, J. Nocedal, and R. Schnabel. Representations of quasi-Newton matrices and their use in limited memory methods. Mathematical Programming, 63 (1):129-156, 1994.
5. V. Chandrasekaran, N. Srebro, and P. Harsha. Complexity of inference in graphical models. In 24th Conference on Uncertainty in Artificial Intelligence (UAI), 2008.
6. J. Edmonds. Matroids and the greedy algorithm. Mathematical Programming, 1(1):127-136, 1971.
7. A. Globerson and T. S. Jaakkola. Convergent propagation algorithms via oriented trees. In 23rd Conference on Uncertainty in Artificial Intelligence (UAI), 2007.
8. J. E. Gonzalez, Y. Low, and C. Guestrin. Residual splash for optimally parallelizing belief propagation. In 12th International Conference on Artificial Intelligence and Statistics (AISTATS), 2009.
9. L. Grippo, F. Lampariello, and S. Lucidi. A nonmonotone line search technique for Newton's method. SIAM Journal on Numerical Analysis, 23:707-716, 1986.
10. T. Hazan and A. Shashua. Convergent messagepassing algorithms for inference over general graphs with convex free energies. In 24th Conference on Uncertainty in Artificial Intelligence (UAI), 2008.
11. T. Heskes. Convexity arguments for efficient minimization of the Bethe and Kikuchi free energies. Journal of Artificial Intelligence Research, 26:153-190, 2006.
12. V. Jojic, S. Gould, and D. Koller. Accelerated dual decomposition for MAP inference. In 27th International Conference on Machine Learning (ICML), 2010.
13. N. Komodakis, N. Paragios, and G. Tziritas. MRF optimization via dual decomposition: Message-passing revisited. In IEEE 11th International Conference on Computer Vision (ICCV), pages 1-8, 2007.
14. T. Meltzer, A. Globerson, and Y. Weiss. Convergent message passing algorithms - a unifying view. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI), 2009.
15. J. M. Mooij. libDAI: A free and open source C++ library for discrete approximate inference in graphical models. Journal of Machine Learning Research, 11:2169-2173, 2010.
16. A. Nedić and V. G. Subramanian. Approximately optimal utility maximization. In IEEE Information Workshop on Networking and Information Theory (ITW), pages 206-210, 2009.
17. J. Nocedal. Updating quasi-Newton matrices with limited storage. Mathematics of Computation, 35:773-782, 1980.
18. M. Schmidt, E. van den Berg, M. Friedlander, and K. Murphy. Optimizing costly functions with simple constraints: A limited-memory projected quasi-Newton algorithm. In 12th International Conference on Artificial Intelligence and Statistics (AISTATS), 2009.
19. M. J. Wainwright, T. S. Jaakkola, and A. S. Willsky. A new class of upper bounds on the log partition function. IEEE Transactions on Information Theory, 51:2313-2335, July 2005a.
20. M. J. Wainwright, T. S. Jaakkola, and A. S. Willsky. MAP estimation via agreement on (hyper) trees: Message-passing and linear-programming approaches. IEEE Transactions on Information Theory, 51(11):3697-3717, 2005b.
21. C.Wang, Q. Liu, and X. Yang. Convergence properties of nonmonotone spectral projected gradient methods. Journal of Computational and Applied Mathematics, 181(1):51-66, 2005.
22. J. S. Yedidia, W. T. Freeman, and Y. Weiss. Understanding belief propagation and its generalizations. In Exploring artificial intelligence in the new millennium, pages 239-269. Morgan Kaufmann Publishers Inc., 2003.