On sampling from the Gibbs distribution with random maximum a-posteriori perturbations

Advances in Neural Information Processing Systems

Volumn , Issue , 2013, Pages

  Hazan, Tamir ^a   Maji, Subhransu ^b   Jaakkola, Tommi ^c  

^a UNIVERSITY OF HAIFA   (Israel)

^b TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO   (United States)

^c MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ENERGY LANDSCAPE; GIBBS DISTRIBUTION; LOW DIMENSIONAL; LOWER BOUNDS; MAP INFERENCES; MAXIMUM A POSTERIORI; PARTITION FUNCTIONS;

EID: 84898967883     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (25)

1. Alexandre Bouchard-Côté and Michael I Jordan. Optimization of structured mean field objectives. In AUAI, pages 67-74, 2009.
2. Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. PAMI, 2001.
3. L.A. Goldberg and M. Jerrum. The complexity of ferromagnetic ising with local fields. Combinatorics Probability and Computing, 16(1):43, 2007.
4. E.J. Gumbel and J. Lieblein. Statistical theory of extreme values and some practical applications: a series of lectures, volume 33. US Govt. Print. Office, 1954.
5. T. Hazan and T. Jaakkola. On the partition function and random maximum a-posteriori perturbations. In Proceedings of the 29th International Conference on Machine Learning, 2012.
6. T. Hazan, S. Maji, Keshet J., and T. Jaakkola. Learning efficient random maximum a-posteriori predictors with non-decomposable loss functions. Advances in Neural Information Processing Systems, 2013.
7. M. Jerrum and A. Sinclair. Polynomial-time approximation algorithms for the ising model. SIAM Journal on computing, 22(5):1087-1116, 1993.
8. M.I. Jordan, Z. Ghahramani, T.S. Jaakkola, and L.K. Saul. An introduction to variational methods for graphical models. Machine learning, 37(2):183-233, 1999.
9. J. Keshet, D. McAllester, and T. Hazan. Pac-bayesian approach for minimization of phoneme error rate. In ICASSP, 2011.
10. Pushmeet Kohli and Philip HS Torr. Measuring uncertainty in graph cut solutions-efficiently computing min-marginal energies using dynamic graph cuts. In ECCV, pages 30-43. 2006.
11. D. Koller and N. Friedman. Probabilistic graphical models. MIT press, 2009.
12. S. Kotz and S. Nadarajah. Extreme value distributions: theory and applications. World Scientific Publishing Company, 2000.
13. A. Kulesza and B. Taskar. Structured determinantal point processes. In Proc. Neural Information Processing Systems, 2010.
14. Qiang Liu and Alexander T Ihler. Negative tree reweighted belief propagation. arXiv preprint arXiv:1203.3494, 2012.
15. Francesco Orabona, Tamir Hazan, Anand D Sarwate, and Tommi. Jaakkola. On measure concentration of random maximum a-posteriori perturbations. arXiv:1310.4227, 2013.
16. G. Papandreou and A. Yuille. Gaussian sampling by local perturbations. In Proc. Int. Conf. on Neural Information Processing Systems (NIPS), pages 1858-1866, December 2010.
17. G. Papandreou and A. Yuille. Perturb-and-map random fields: Using discrete optimization to learn and sample from energy models. In ICCV, Barcelona, Spain, November 2011.
18. Nicholas Ruozzi. The bethe partition function of log-supermodular graphical models. arXiv preprint arXiv:1202.6035, 2012.
19. D. Sontag, T. Meltzer, A. Globerson, T. Jaakkola, and Y. Weiss. Tightening LP relaxations for MAP using message passing. In Conf. Uncertainty in Artificial Intelligence (UAI), 2008.
20. E.B. Sudderth, M.J. Wainwright, and A.S. Willsky. Loop series and Bethe variational bounds in attractive graphical models. Advances in neural information processing systems, 20, 2008.
21. D. Tarlow, R.P. Adams, and R.S. Zemel. Randomized optimum models for structured prediction. In Proceedings of the 15th Conference on Artificial Intelligence and Statistics, 2012.
22. M. J. Wainwright, T. S. Jaakkola, and A. S. Willsky. A new class of upper bounds on the log partition function. Trans. on Information Theory, 51(7):2313-2335, 2005.
23. Max Welling. Herding dynamical weights to learn. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 1121-1128. ACM, 2009.
24. T. Werner. High-arity interactions, polyhedral relaxations, and cutting plane algorithm for soft constraint optimisation (map-mrf). In CVPR, pages 1-8, 2008.
25. J. Zhang, H. Liang, and F. Bai. Approximating partition functions of the two-state spin system. Information Processing Letters, 111(14):702-710, 2011.