Imprecise probability models for learning multinomial distributions from data. Applications to learning credal networks

International Journal of Approximate Reasoning

Volumn 55, Issue 7, 2014, Pages 1548-1569

  Masegosa, Andrés R ^a   Moral, Serafín ^a  

^a UNIVERSITY OF GRANADA   (Spain)

Author keywords

Credal networks; Ignorance; Imprecise prior models; Imprecise probability; Learning

Indexed keywords

BAYESIAN NETWORKS; GRAPHIC METHODS;

CREDAL NETWORKS; DIRICHLET DISTRIBUTIONS; IGNORANCE; IMPRECISE DIRICHLET MODEL; IMPRECISE PROBABILITIES; IMPRECISE PROBABILITY MODELS; LEARNING; MULTINOMIAL DISTRIBUTIONS;

PROBABILITY DISTRIBUTIONS;

EID: 84905092621     PISSN: 0888613X     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ijar.2013.09.019     Document Type: Article

References (50)

1. S. Moral Imprecise probabilities for representing ignorance about a parameter Int. J. Approx. Reason. 53 2012 347 362 10.1016/j.ijar.2010.12.001
2. E. Jaynes Prior probabilities IEEE Trans. Syst. Sci. Cybern. 4 1968 227 241
3. H. Jeffreys Theory of Probability 3rd edition 1983 Clarendon Press Oxford
4. R. Kass, and L. Wasserman The selection of prior distributions by formal rules J. Am. Stat. Assoc. 435 1996 1343 1370
5. P. Walley, and S. Moral Upper probabilities based only in the likelihood function J. R. Stat. Soc. B 61 1996 831 847
6. P. Walley Statistical Reasoning with Imprecise Probabilities 1991 Chapman and Hall London
7. J. Keynes A Treatise on Probability 1921 Macmillan London
8. P. Walley Inferences from multinomial data: learning about a bag of marbles (with discussion) J. R. Stat. Soc. B 58 1996 3 57
9. J. Bernard An introduction to the imprecise Dirichlet model for multinomial data Int. J. Approx. Reason. 39 2005 123 150 (Pubitemid 40467337)
10. G. de Cooman, E. Miranda, and E. Quaeghebeur Representation insensitivity in immediate prediction under exchangeability Int. J. Approx. Reason. 50 2009 204 216
11. F. Coolen An imprecise Dirichlet model for Bayesian analysis of failure data including right-censored observations Reliab. Eng. Syst. Saf. 56 1997 61 68 (Pubitemid 127391830)
12. J. Bernard Implicative analysis for multivariate binary data using an imprecise Dirichlet model J. Stat. Plan. Inference 105 2002 83 103
13. M. Zaffalon Statistical inference of the naive credal classifier G. de Cooman, T. Fine, T. Seidenfeld, Proceedings of the Second International Symposium on Imprecise Probabilities and Their Applications 2001 Shaker Publishing 384 393
14. E. Quaeghebeur, and G. de Cooman Learning in games using the imprecise Dirichlet model Int. J. Approx. Reason. 50 2009 243 256
15. M. Troffaes, and F. Coolen Applying the imprecise Dirichlet model in cases with partial observations and dependencies in failure data Int. J. Approx. Reason. 50 2009 257 268
16. A. Piatti, M. Zaffalon, F. Trojani, and M. Hutter Learning about a categorical latent variable under prior near-ignorance G. de Cooman, J. Vejnarová, M. Zaffalon, Proceedings of the Fifth International Symposium om Imprecise Probability: Theories and Applications (ISIPTA'07) 2007 357 364
17. A. Piatti, M. Zaffalon, F. Trojani, and M. Hutter Limits of learning about a categorical latent variable under prior near-ignorance Int. J. Approx. Reason. 50 2009 597 611
18. Abellán, and S. Moral A new imprecise score measure for independence Intell. Data Anal. 16 2012 1847 1863
19. F. Coolen, and T. Augustin A nonparametric predictive alternative to the imprecise Dirichlet model: The case of a known number of categories Int. J. Approx. Reason. 50 2009 217 230
20. J. Pearl Probabilistic Reasoning with Intelligent Systems 1988 Morgan & Kaufman San Mateo
21. F. Cozman Credal networks Artif. Intell. 120 2000 199 233
22. E. Bauer, and R. Kohavi An empirical comparison of voting classification algorithms: Bagging, boosting, and variants Mach. Learn. 36 1999 105 139
23. F. Provost, and P. Domingos Tree induction for probability-based ranking Mach. Learn. 52 2003 199 215
24. J. Bernardo Reference posterior distributions for Bayesian inference (with discussion) J. R. Stat. Soc. B 41 1979 113 147
25. D. Geiger, and D. Heckerman A characterization of the Dirichlet distribution through global and local parameter independence Ann. Stat. 3 1997 1344 1369
26. R. Neapolitan Learning Bayesian Networks 2004 Prentice Hall Upper Saddle River, NJ
27. J. Bernard The imprecise Dirichlet model Int. J. Approx. Reason. 50 2009 201 203
28. J.M. Bernard The Imprecise Dirichlet Model Int. J. Approx. Reason. 50 2009 201 268 (special section)
29. C.P. de Campos, and A. Benavoli Inference with multinomial data: Why to weaken the prior strength T. Walsh, Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI 2011) 2011 IJCAI/AAAI 2107 2112
30. A. Cano, M. Gómez-Olmedo, A. Masegosa, and S. Moral Locally averaged Bayesian Dirichlet metrics for learning the structure and the parameters of Bayesian networks Int. J. Approx. Reason. 54 2013 526 540 10.1016/j.ijar.2012.09.003
31. D. Heckerman, D. Geiger, and D. Chickering Learning Bayesian networks: The combination of knowledge and statistical data Mach. Learn. 20 1995 197 243
32. G. Cooper, and E. Herskovits A Bayesian method for the induction of probabilistic networks from data Mach. Learn. 9 1992 309 347
33. S. Acid, and L. de Campos Learning Bayesian network classifiers: Searching in a space of partially directed acyclic graphs Mach. Learn. 59 2005 213 235 (Pubitemid 40890478)
34. G. de Cooman, F. Hermans, A. Antonucci, and M. Zaffalon Epistemic irrelevance in credal nets: The case of imprecise Markov trees Int. J. Approx. Reason. 51 2010 1029 1052
35. I. Levi The Enterprise of Knowledge 1980 MIT Press London
36. D. Chickering Learning Bayesian networks is NP-complete D. Fisher, H. Lenz, Learning from Data: Artificial Intelligence and Statistics V 1996 Springer-Verlag 121 130
37. S. Moral An empirical comparison of score measures for independence Proceedings of the Tenth International Conference IPMU 2004, vol. 2 2004 1307 1314
38. T. Silander, P. Kontkanen, and P. Myllymäki On sensitivity of the MAP Bayesian network structure to the equivalent sample size parameter R. Parr, L. van der Gaag, Proceedings of the 23rd Conference on Uncertainty in Artificial Intelligence (UAI-2007) 2007 AUAI Press 360 367
39. H. Steck, and T. Jaakkola On the Dirichlet prior and Bayesian regularization S. Becker, S. Thrun, K. Obermayer, Advances in Neural Information Processing Systems (NIPS 2002) 2002 MIT Press 697 704
40. S. van Dijk, L. can der Gaag, and D. Thierens A skeleton-based approach to learning Bayesian networks from data N. Lavrač, D. Gamberger, L. Todorovski, H. Blockeel, Proceedings of the Seventh Conference on Principles and Practice of Knowledge Discovery in Databases 2003 Springer-Verlag 132 143 (Pubitemid 37231091)
41. A. Masegosa, and S. Moral New skeleton-based approaches for Bayesian structure learning of Bayesian networks Appl. Soft Comput. 13 2013 1110 1120
42. A. Cano, J. Cano, and S. Moral Convex sets of probabilities propagation by simulated annealing Proceedings of the Fifth International Conference IPMU'94, Paris 1994 4 8
43. A. Antonucci, and M. Zaffalon Decision-theoretic specification of credal networks: a unified language for uncertain modeling with sets of Bayesian networks Int. J. Approx. Reason. 49 2008 345 361
44. A. Cano, M. Gómez-Olmedo, S. Moral, and J. Abellán Hill-climbing and branch-and-bound algorithms for exact and approximate inference in credal networks Int. J. Approx. Reason. 44 2007 261 280 (Pubitemid 46149240)
45. A. Frank, and A. Asuncion UCI machine learning repository http://archive.ics.uci.edu/ml 2010
46. G. Corani, and M. Zaffalon Learning reliable classifiers from small or incomplete data sets: the naive credal classifier 2 J. Mach. Learn. Res. 9 2008 581 621
47. G. Corani, and A. Benavoli Restricting the IDM for classification Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Methods 2010 Springer 328 337
48. M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I.H. Witten The Weka data mining software: an update ACM SIGKDD Explor. Newsl. 11 1 2009 10 18
49. G. Corani, and M. Zaffalon Credal model averaging: An extension of Bayesian model averaging to imprecise probabilities Machine Learning and Knowledge Discovery in Databases 2008 Springer 257 271
50. M. Zaffalon, G. Corani, and D. Mauá Evaluating credal classifiers by utility-discounted predictive accuracy Int. J. Approx. Reason. 53 8 2012 1282 1301 10.1016/j.ijar.2012.06.022