Barrier Frank-Wolfe for marginal inference

Advances in Neural Information Processing Systems

Volumn 2015-January, Issue , 2015, Pages 532-540

  Krishnan, Rahul G ^a   Lacoste Julien, Simon ^b   Sontag, David ^a  

^a NEW YORK UNIVERSITY   (United States)

^b ECOLE NORMALE SUPÉRIEURE   (France)

Author keywords

[No Author keywords available]

Indexed keywords

GRADIENT METHODS; INFERENCE ENGINES; INFORMATION SCIENCE; TREES (MATHEMATICS);

CONDITIONAL GRADIENT METHOD; GLOBALLY CONVERGENT ALGORITHMS; LOCAL CONSISTENCY; MARGINAL POLYTOPE; MAXIMUM A POSTERIORI; MODULAR STRUCTURES; QUALITY OF RESULTS; VARIATIONAL INFERENCE;

ALGORITHMS;

EID: 84965120278     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (30)

1. D. Allouche, S. de Givry, and T. Schiex. Toulbar2, an open source exact cost function network solver, 2010.
2. B. Andres, B. T., and J. H. Kappes. OpenGM: A C++ library for discrete graphical models, June 2012.
3. D. Belanger, D. Sheldon, and A. McCallum. Marginal inference in MRFs using Frank-Wolfe. NIPS Workshop on Greedy Optimization, Frank-Wolfe and Friends, 2013.
4. J. Besag. On the statistical analysis of dirty pictures. J R Stat Soc Series B, 1986.
5. E. Borenstein and S. Ullman. Class-specific, top-down segmentation. In ECCV, 2002.
6. Y. Boykov and V. Kolmogorov. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. TPAMI, 2004.
7. J. Domke. Learning graphical model parameters with approximate marginal inference. TPAMI, 2013.
8. S. Ermon, C. P. Gomes, A. Sabharwal, and B. Selman. Taming the curse of dimensionality: Discrete integration by hashing and optimization. In ICML, 2013.
9. D. Garber and E. Hazan. A linearly convergent conditional gradient algorithm with applications to online and stochastic optimization. arXiv preprint arXiv:1301.4666, 2013.
10. A. Globerson and T. Jaakkola. Convergent propagation algorithms via oriented trees. In UAI, 2007.
11. I. Gurobi Optimization. Gurobi optimizer reference manual, 2015.
12. T. Hazan and T. Jaakkola. On the partition function and random maximum a-posteriori perturbations. In ICML, 2012.
13. M. Jaggi. Revisiting Frank-Wolfe: Projection-free sparse convex optimization. In ICML, 2013.
14. J. Jancsary and G. Matz. Convergent decomposition solvers for tree-reweighted free energies. In AISTATS, 2011.
15. J. Kappes et al. A comparative study of modern inference techniques for discrete energy minimization problems. In CVPR, 2013.
16. V. Kolmogorov. Convergent tree-reweighted message passing for energy minimization. TPAMI, 2006.
17. V. Kolmogorov and C. Rother. Minimizing nonsubmodular functions with graph cuts-A Review. TPAMI, 2007.
18. T. Koo, A. Globerson, X. Carreras, and M. Collins. Structured prediction models via the matrix-tree theorem. In EMNLP-CoNLL, 2007.
19. S. Lacoste-Julien and M. Jaggi. On the global linear convergence of Frank-Wolfe optimization variants. In NIPS, 2015.
20. S. Lacoste-Julien, M. Jaggi, M. Schmidt, and P. Pletscher. Block-coordinate Frank-Wolfe optimization for structural SVMs. In ICML, 2013.
21. B. London, B. Huang, and L. Getoor. The benefits of learning with strongly convex approximate inference. In ICML, 2015.
22. J. M. Mooij. libDAI: A free and open source C++ library for discrete approximate inference in graphical models. JMLR, 2010.
23. S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, and P. Kohli. Decision tree fields. In ICCV, 2011.
24. G. Papandreou and A. Yuille. Perturb-and-map random fields: Using discrete optimization to learn and sample from energy models. In ICCV, 2011.
25. R. Salakhutdinov. Learning and evaluating Boltzmann machines. Technical report, 2008.
26. S. Shimony. Finding MAPs for belief networks is NP-hard. Artificial Intelligence, 1994.
27. D. Sontag and T. Jaakkola. New outer bounds on the marginal polytope. In NIPS, 2007.
28. D. Sontag, T. Meltzer, A. Globerson, Y. Weiss, and T. Jaakkola. Tightening LP relaxations for MAP using message-passing. In UAI, 2008.
29. 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, 2005.
30. S. Wang, R. Frostig, P. Liang, and C. Manning. Relaxations for inference in restricted Boltzmann machines. In ICLR Workshop, 2014.