Advanced search
1 file | 1.03 MB Add to list

Coherent predictive inference under exchangeability with imprecise probabilities

Author
Organization
Abstract
Coherent reasoning under uncertainty can be represented in a very general manner by coherent sets of desirable gambles. In a context that does not allow for indecision, this leads to an approach that is mathematically equivalent to working with coherent conditional probabilities. If we do allow for indecision, this leads to a more general foundation for coherent (imprecise-) probabilistic inference. In this framework, and for a given finite category set, coherent predictive inference under exchangeability can be represented using Bernstein coherent cones of multivariate polynomials on the simplex generated by this category set. This is a powerful generalisation of de Finetti's Representation Theorem allowing for both imprecision and indecision. We define an inference system as a map that associates a Bernstein coherent cone of polynomials with every finite category set. Many inference principles encountered in the literature can then be interpreted, and represented mathematically, as restrictions on such maps. We discuss, as particular examples, two important inference principles: representation insensitivity-a strengthened version of Walley's representation invariance-and specificity. We show that there is an infinity of inference systems that satisfy these two principles, amongst which we discuss in particular the skeptically cautious inference system, the inference systems corresponding to (a modified version of) Walley and Bernard's Imprecise Dirichlet Multinomial Models (IDMM), the skeptical IDMM inference systems, and the Haldane inference system. We also prove that the latter produces the same posterior inferences as would be obtained using Haldane's improper prior, implying that there is an infinity of proper priors that produce the same coherent posterior inferences as Haldane's improper one. Finally, we impose an additional inference principle that allows us to characterise uniquely the immediate predictions for the IDMM inference systems.
Keywords
SETS, REPRESENTATION, LOWER PREVISIONS, DESIRABLE GAMBLES, MULTINOMIAL DATA, IGNORANCE, MODEL

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.03 MB

Citation

Please use this url to cite or link to this publication:

MLA
De Cooman, Gert, et al. “Coherent Predictive Inference under Exchangeability with Imprecise Probabilities.” JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, vol. 52, 2015, pp. 1–95, doi:10.1613/jair.4490.
APA
De Cooman, G., De Bock, J., & Alves Diniz, M. (2015). Coherent predictive inference under exchangeability with imprecise probabilities. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 52, 1–95. https://doi.org/10.1613/jair.4490
Chicago author-date
De Cooman, Gert, Jasper De Bock, and Márcio Alves Diniz. 2015. “Coherent Predictive Inference under Exchangeability with Imprecise Probabilities.” JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH 52: 1–95. https://doi.org/10.1613/jair.4490.
Chicago author-date (all authors)
De Cooman, Gert, Jasper De Bock, and Márcio Alves Diniz. 2015. “Coherent Predictive Inference under Exchangeability with Imprecise Probabilities.” JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH 52: 1–95. doi:10.1613/jair.4490.
Vancouver
1.
De Cooman G, De Bock J, Alves Diniz M. Coherent predictive inference under exchangeability with imprecise probabilities. JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH. 2015;52:1–95.
IEEE
[1]
G. De Cooman, J. De Bock, and M. Alves Diniz, “Coherent predictive inference under exchangeability with imprecise probabilities,” JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, vol. 52, pp. 1–95, 2015.
@article{5930684,
  abstract     = {{Coherent reasoning under uncertainty can be represented in a very general manner by coherent sets of desirable gambles. In a context that does not allow for indecision, this leads to an approach that is mathematically equivalent to working with coherent conditional probabilities. If we do allow for indecision, this leads to a more general foundation for coherent (imprecise-) probabilistic inference. In this framework, and for a given finite category set, coherent predictive inference under exchangeability can be represented using Bernstein coherent cones of multivariate polynomials on the simplex generated by this category set. This is a powerful generalisation of de Finetti's Representation Theorem allowing for both imprecision and indecision.
 
We define an inference system as a map that associates a Bernstein coherent cone of polynomials with every finite category set. Many inference principles encountered in the literature can then be interpreted, and represented mathematically, as restrictions on such maps. We discuss, as particular examples, two important inference principles: representation insensitivity-a strengthened version of Walley's representation invariance-and specificity. We show that there is an infinity of inference systems that satisfy these two principles, amongst which we discuss in particular the skeptically cautious inference system, the inference systems corresponding to (a modified version of) Walley and Bernard's Imprecise Dirichlet Multinomial Models (IDMM), the skeptical IDMM inference systems, and the Haldane inference system. We also prove that the latter produces the same posterior inferences as would be obtained using Haldane's improper prior, implying that there is an infinity of proper priors that produce the same coherent posterior inferences as Haldane's improper one. Finally, we impose an additional inference principle that allows us to characterise uniquely the immediate predictions for the IDMM inference systems.}},
  author       = {{De Cooman, Gert and De Bock, Jasper and Alves Diniz, Márcio}},
  issn         = {{1076-9757}},
  journal      = {{JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH}},
  keywords     = {{SETS,REPRESENTATION,LOWER PREVISIONS,DESIRABLE GAMBLES,MULTINOMIAL DATA,IGNORANCE,MODEL}},
  language     = {{eng}},
  pages        = {{1--95}},
  title        = {{Coherent predictive inference under exchangeability with imprecise probabilities}},
  url          = {{http://doi.org/10.1613/jair.4490}},
  volume       = {{52}},
  year         = {{2015}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: