Abstract
We introduce a set of transformations on the set of all probability distributions over a finite state space, and show that these transformations are the only ones that preserve certain elementary probabilistic relationships. This result provides a new perspective on a variety of probabilistic inference problems in which invariance considerations play a role. Two particular applications we consider in this paper are the development of an equivariance-based approach to the problem of measure selection, and a new justification for Haldane’s prior as the distribution that encodes prior ignorance about the parameter of a multinomial distribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Carnap, R.: Logical Foundations of Probability. The University of Chicago Press, Chicago (1950)
Gabbay, D.: Theoretical foundations for nonmonotonic reasoning in expert systems. In: Apt, K. (ed.) Logics and Models of Cuncurrent Systems. Springer, Berlin (1985)
Hacking, I.: The Emergence of Probability: a Philosophical Study of Early Ideas About Probability, Induction and Statistical Inference. Cambridge University Press, Cambridge (1975)
Haldane, J.B.S.: A note on inverse probability. In: Proceedings of the Cambridge Philosophical Society, vol. 28, pp. 55–61 (1932)
Hartigan, J.: Invariant prior distributions. Annals of Mathematical Statistics 35(2), 836–845 (1964)
Holbrook, J., Kim, S.S.: Bertrand’s paradox revisited. The Mathematical Intelligencer, 16–19 (2000)
Jaeger, M.: Minimum cross-entropy reasoning:A statistical justification. In: Mellish, C.S. (ed.) Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI 1995), Montréal, Canada, pp. 1847–1852. Morgan Kaufmann, San Francisco (1995)
Jaeger, M.: Constraints as data: A new perspective on inferring probabilities. In: Nebel, B. (ed.) Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI 2001), pp. 755–760 (2001)
Jaeger, M.: Arepresentation theorem and applications to measure selection and noninformative priors. Technical Report MPI-I-2003-2-002, Max-Planck-Institut für Informatik (2003) (in preparation)
Jaynes, E.T.: Prior probability. IEEE Transactions on Systems Science and Cybernetics 4(3), 227–241 (1968)
Jeffreys, H.: Theory of Probability, 3rd edn. Oxford University Press, Oxford (1961)
Paris, J.: On filling-in missing information in causal networks. Submitted to Knowledge-based Systems.
Paris, J.: Common sense and maximum entropy. Synthese 117, 75–93 (1999)
Paris, J.B.: The Uncertain Reasoner’s Companion. Cambridge University Press, Cambridge (1994)
Paris, J.B., Vencovská, A.: A note on the inevitability of maximum entropy. International Journal of Approximate Reasoning 4, 183–223 (1990)
Reichenbach, H.: The Theory of Probability. University of California Press, Los Angeles (1949)
Schafer, J.L.: Analysis of Incomplete Multivariate Data. Chapman & Hall/CRC (1997)
Shore, J.E., Johnson, R.W.: Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. IEEE Transactions on Information Theory IT-26(1), 26–37 (1980)
van Fraassen, B.C.: Laws and Symmetry. Clarendon, Oxford (1989)
Villegas, C.: On the representation of ignorance. Journal of the American Statistical Association 72, 651–654 (1977)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jaeger, M. (2003). A Representation Theorem and Applications. In: Nielsen, T.D., Zhang, N.L. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2003. Lecture Notes in Computer Science(), vol 2711. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45062-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-45062-7_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40494-1
Online ISBN: 978-3-540-45062-7
eBook Packages: Springer Book Archive