Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A note on incorrect inferences in non-binary qualitative probabilistic networks (2208.09344v3)

Published 19 Aug 2022 in cs.AI, math.ST, stat.ME, and stat.TH

Abstract: Qualitative probabilistic networks (QPNs) combine the conditional independence assumptions of Bayesian networks with the qualitative properties of positive and negative dependence. They formalise various intuitive properties of positive dependence to allow inferences over a large network of variables. However, we will demonstrate in this paper that, due to an incorrect symmetry property, many inferences obtained in non-binary QPNs are not mathematically true. We will provide examples of such incorrect inferences and briefly discuss possible resolutions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Introducing situational signs in qualitative probabilistic networks. International Journal of Approximate Reasoning, 38(Special Issue):333–354, 2005. doi: 10.1016/j.ijar.2004.05.009.
  2. Some notions of multivariate positive dependence. Insurance: Mathematics and Economics, 37(1 SPEC. ISS.):13–26, 2005. ISSN 01676687. doi: 10.1016/j.insmatheco.2004.09.004.
  3. Adnan Darwiche. Modeling and reasoning with Bayesian networks. Cambridge university press, 2009.
  4. Complexity of inferences in polytree-shaped semi-qualitative probabilistic networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 27, pages 217–223, 2013.
  5. Semi-qualitative probabilistic networks in computer vision problems. Journal of Statistical Theory and Practice, 3(1):197–210, 2009. ISSN 15598616. doi: 10.1080/15598608.2009.10411920.
  6. Belief Updating and Learning in Semi-Qualitative Probabilistic Networks. In Conference on Uncertainty in Artificial Intelligence, pages 153–160, 2005.
  7. Efficient reasoning in qualitative probabilistic networks. In Proceedings of the 11th National Conference on Artificial Intelligence (AAAI-93), pages 548–553, Menlo Park, 1993a. AAAI Press/The MIT Press.
  8. Intercausal reasoning with uninstantiated ancestor nodes. In Proceedings of the Ninth Annual Conference on Uncertainty in Artificial Intelligence (UAI-93), pages 317–325, San Francisco, 1993b. Morgan Kaufmann Publishers.
  9. Association of Random Variables, with Applications. The Annals of Mathematical Statistics, 38(5):1466 – 1474, 1967. doi: 10.1214/aoms/1177698701. URL https://doi.org/10.1214/aoms/1177698701.
  10. Total positivity in markov structures. The Annals of Statistics, pages 1152–1184, 2017.
  11. A decision-theoretic approach to the display of information for timecritical decisions: The Vista project. In Proceedings of SOAR-92 Conference on Space Operations Automation and Research, National Aeronautics and Space Administration, 1992.
  12. Probabilistic graphical models: principles and techniques. MIT press, 2009.
  13. Maximum likelihood estimation in gaussian models under total positivity. The Annals of Statistics, 47(4):1835–1863, 2019.
  14. E L Lehmann. Some Concepts of Dependence. The Annals of Mathematical Statistics, 37(5):1137–1153, 1966. ISSN 1098-6596. doi: 10.1017/CBO9781107415324.004.
  15. Haim Levy. Stochastic dominance: Investment decision making under uncertainty. Springer, 2015.
  16. Positivity in linear gaussian structural equation models. arXiv preprint arXiv:2305.19884, 2023.
  17. Sign fusion of multiple QPNs based on qualitative mutual information. International Journal of Computational Science and Engineering, 19:36, 2019. doi: 10.1504/IJCSE.2019.099650.
  18. Handbook of Graphical Models. CRC Press, Boca Raton, 1st edition, 2018. ISBN 9780429463976. doi: https://0-doi-org.pugwash.lib.warwick.ac.uk/10.1201/9780429463976.
  19. Paul R. Milgrom. Good News and Bad News: Representation Theorems and Applications. The Bell Journal of Economics, 12(2):380, 1981. ISSN 0361915X. doi: 10.2307/3003562.
  20. Simon Parsons. Refining reasoning in qualitative probabilistic networks. In Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence, pages 427–434, Montreal, 1995.
  21. Learning bipartite bayesian networks under monotonicity restrictions. International Journal of General Systems, 49(1):88–111, 2020.
  22. Silja Renooij and Linda C. van der Gaag. Decision Making in Qualitative Influence Diagrams. In D.J. Cook, editor, Proceedings of the Eleventh International FLAIRS Conference, pages 410–414, Menlo Park, 1998. AAAI Press.
  23. Silja Renooij and Linda C. van der Gaag. Enhancing QPNs for Trade-off Resolution. In K.B. Laskey and H. Prade, editors, Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 559–566, San Francisco, 1999. Morgan Kaufmann Publishers.
  24. Silja Renooij and Linda C. van der Gaag. Exploiting Non-monotonic Influences in Qualitative Belief Networks. In Proceedings of the Eighth International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU), pages 1285–1290, Madrid, 2000.
  25. Silja Renooij and Linda C. van der Gaag. From Qualitative to Quantitative Probabilistic Networks. In A. Darwiche and N. Friedman, editors, Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 422–429, San Francisco, 2002. Morgan Kaufmann Publishers.
  26. Silja Renooij and Linda C. van der Gaag. Enhanced qualitative probabilistic networks for resolving trade-offs. Artificial Intelligence, 172(12-13):1470–1494, 2008. doi: 10.1016/j.artint.2008.04.001.
  27. Zooming in on Trade-offs in Qualitative Probabilistic Networks. In J. Etheredge and B. Manaris, editors, Proceedings of the Thirteenth International FLAIRS Conference, pages 303–307, Menlo Park, 2000a. AAAI Press.
  28. Pivotal Pruning of Trade-offs in QPNs. In G. Boutilier and M. Goldszmidt, editors, Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 515–522, San Francisco, 2000b. Morgan Kaufmann Publishers.
  29. Propagation of Multiple Observations in QPNs Revisited. In F. van Harmelen, editor, Proceedings of the Fifteenth European Conference on Artificial Intelligence (ECAI), Vol 77, Frontiers in Artificial Intelligence and Applications, pages 665–669, Amsterdam, 2002a. IOS Press.
  30. Context-specific sign-propagation in qualitative probabilistic networks. Artificial Intelligence, 140:207–230, 2002b.
  31. Using Kappas as Indicators of Strength in Qualitative Probabilistic Networks. In T.D. Nielsen and N.L. Zhang, editors, Proceedings of the Seventh European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU), pages 87–99. Springer Verlag, 2003.
  32. Estimation of positive definite M-matrices and structure learning for attractive Gaussian Markov random fields. Linear Algebra and Its Applications, 473:145–179, 2015. ISSN 00243795. doi: 10.1016/j.laa.2014.04.020.
  33. Linda C. van der Gaag and Philippe Leray. Qualitative probabilistic relational models. In Davide Ciucci, Gabriella Pasi, and Barbara Vantaggi, editors, Scalable Uncertainty Management, pages 276–289, Cham, 2018. Springer International Publishing. ISBN 978-3-030-00461-3.
  34. Probability Assessments from Multiple Experts : Qualitative Information is More Robust. In Proceedings of the Twenty-Second Benelux Conference on Artificial Intelligence (BNAIC), Luxembourg, 2010.
  35. Inference in qualitative probabilistic networks revisited. International Journal of Approximate Reasoning, 50(5):708–720, 2009. ISSN 0888-613X. doi: 10.1016/j.ijar.2008.12.001. URL http://dx.doi.org/10.1016/j.ijar.2008.12.001.
  36. Learning high-dimensional gaussian graphical models under total positivity without adjustment of tuning parameters. In International Conference on Artificial Intelligence and Statistics, pages 2698–2708. PMLR, 2020.
  37. Michael P. Wellman. Fundamental Concepts of Qualitative Probabilistic Networks. Artificial Intelligence, 44(3):257–303, 1990a.
  38. Michael P. Wellman. Graphical Inference in Qualitative Probabilistic Networks. Networks, 20(5):687–701, 1990b.
  39. Explaining “Explaining Away”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(3):287–292, 1993.
  40. Qualitative probabilistic networks with reduced ambiguities. Applied Intelligence, 33(2):159–178, 2010. doi: 10.1007/s10489-008-0156-5.
  41. Extending Qualitative Probabilistic Network with Mutual Information Weights. International Journal of Intelligence Science, 05(03):133–144, 2015. ISSN 2163-0283. doi: 10.4236/ijis.2015.53012.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now