Simple MAP inference via low-rank relaxations

Advances in Neural Information Processing Systems

Volumn 4, Issue January, 2014, Pages 3077-3085

  Frostig, Roy ^a   Wang, Sida I ^a   Liang, Percy ^a   Manning, Christopher D ^a  

^a Stanford University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

INFORMATION SCIENCE; MARKOV PROCESSES;

BINARY VARIABLES; DISCRETE PROBLEMS; MAP INFERENCES; MARKOV RANDOM FIELDS; MAXIMUM A POSTERIORI; PAIRWISE INTERACTION; SEMIDEFINITE RELAXATION; THEORETICAL BOUNDS;

INFERENCE ENGINES;

EID: 84937942720     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 6: 721-741, 1984.
2. D. Sontag, T. Meltzer, A. Globerson, Y. Weiss, and T. Jaakkola. Tightening LP relaxations for MAP using message-passing. In Uncertainty in Artificial Intelligence (UAI), pages 503-510, 2008.
3. A. Rush, D. Sontag, M. Collins, and T. Jaakkola. On dual decomposition and linear programming relaxations for natural language processing. In Empirical Methods in Natural Language Processing (EMNLP), pages 1-11, 2010.
4. M. Wainwright and M. I. Jordan. Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning, 1: 1-307, 2008.
5. M. Goemans and D. Williamson. Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. Journal of the ACM (JACM), 42(6): 1115-1145, 1995.
6. Y. Nesterov. Semidefinite relaxation and nonconvex quadratic optimization. Optimization methods and software, 9: 141-160, 1998.
7. N. Alon and A. Naor. Approximating the cut-norm via Grothendieck's inequality. SIAM Journal on Computing, 35(4): 787-803, 2006.
8. S. Burer and R. Monteiro. A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization. Mathematical Programming, 95(2): 329-357, 2001.
9. A. I. Barvinok. Problems of distance geometry and convex properties of quadratic maps. Discrete & Computational Geometry, 13: 189-202, 1995.
10. G. Pataki. On the rank of extreme matrices in semidefinite programs and the multiplicity of optimal eigenvalues. Mathematics of Operations Research, 23(2): 339-358, 1998.
11. P. Krähenbühl and V. Koltun. Efficient inference in fully connected CRFs with Gaussian edge potentials. In Advances in Neural Information Processing Systems (NIPS), 2011.
12. S. Burer and R. Monteiro. Local minima and convergence in low-rank semidefinite programming. Mathematical Programming, 103(3): 427-444, 2005.
13. J. Briët, F. M. d. O. Filho, and F. Vallentin. The positive semidefinite Grothendieck problem with rank constraint. In Automata, Languages and Programming, pages 31-42, 2010.
14. I. J. Schoenberg. Positive definite functions on spheres. Duke Mathematical Journal, 9: 96-108, 1942.
15. M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul. An introduction to variational methods for graphical models. Machine Learning, 37: 183-233, 1999.
16. P. Krähenbühl and V. Koltun. Parameter learning and convergent inference for dense random fields. In International Conference on Machine Learning (ICML), pages 513-521, 2013.
17. B. Kulis, A. C. Surendran, and J. C. Platt. Fast low-rank semidefinite programming for embedding and clustering. In Artificial Intelligence and Statistics (AISTATS), pages 235-242, 2007.
18. B. Recht and C. Ré. Parallel stochastic gradient algorithms for large-scale matrix completion. Mathematical Programming Computation, 5: 1-26, 2013.
19. J. Lee, B. Recht, N. Srebro, J. Tropp, and R. Salakhutdinov. Practical large-scale optimization for maxnorm regularization. In Advances in Neural Information Processing Systems (NIPS), pages 1297-1305, 2010.
20. S. Wang, R. Frostig, P. Liang, and C. Manning. Relaxations for inference in restricted Boltzmann machines. In International Conference on Learning Representations (ICLR), 2014.
21. D. Sontag and T. Jaakkola. New outer bounds on the marginal polytope. In Advances in Neural Information Processing Systems (NIPS), pages 1393-1400, 2008.