Hostname: page-component-78c5997874-ndw9j Total loading time: 0 Render date: 2024-11-20T01:45:22.072Z Has data issue: false hasContentIssue false
  • English
  • Français

ON THE TRUTH-CONVERGENCE OF OPEN-MINDED BAYESIANISM

Part of: Foundational and philosophical topics

Published online by Cambridge University Press:  22 February 2021

TOM F. STERKENBURG  and
RIANNE DE HEIDE
TOM F. STERKENBURG
Affiliation:
MUNICH CENTER FOR MATHEMATICAL PHILOSOPHY LUDWIG-MAXIMILIANS-UNIVERSITY MUNICH GESCHWISTER-SCHOLL-PLATZ 1, 80539MUNICH, GERMANYE-mail: [email protected]
RIANNE DE HEIDE
Affiliation:
MACHINE LEARNING GROUP CENTRUM WISKUNDE & INFORMATICA SCIENCE PARK 123, 1098XG, THE NETHERLANDS and MATHEMATICAL INSTITUTE LEIDEN UNIVERSITY NIELS BOHRWEG 1, 2333CA LEIDEN, THE NETHERLANDS E-mail: [email protected]
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Wenmackers and Romeijn [38] formalize ideas going back to Shimony [33] and Putnam [28] into an open-minded Bayesian inductive logic, that can dynamically incorporate statistical hypotheses proposed in the course of the learning process. In this paper, we show that Wenmackers and Romeijn’s proposal does not preserve the classical Bayesian consistency guarantee of merger with the true hypothesis. We diagnose the problem, and offer a forward-looking open-minded Bayesians that does preserve a version of this guarantee.

Keywords

inductive logicBayesianismtruth-convergence

MSC classification

Primary: 62A01: Foundations and philosophical topics
Type
Research Article
Information
The Review of Symbolic Logic , Volume 15 , Issue 1 , March 2022 , pp. 64 - 100
Check for updates
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Copyright
© The Author(s), 2021. Published by Cambridge University Press on behalf of The Association for Symbolic Logic

References

Barnard, G. A. & Cox, D. R., editors. (1962). The Foundations of Statistical Inference: A Discussion. Methuen’s Monographs on Applied Probability and Statistics. London: Methuen.Google Scholar
Belot, G. (2013). Bayesian orgulity. Philosophy of Science, 80(4), 483–503.CrossRefGoogle Scholar
Blackwell, D. & Dubins, L. (1962). Merging of opinion with increasing information. The Annals of Mathematical Statistics, 33, 882–886.CrossRefGoogle Scholar
Cesa-Bianchi, N. & Lugosi, G. (2006). Prediction, Learning and Games. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
Chernov, A. & Vovk, V. G. (2009). Prediction with expert evaluators’ advice. In Gavaldà, R., Lugosi, G., Zeugmann, T., and Zilles, S., editors. Proceedings of the 20th International Conference on Algorithmic Learning Theory. Lecture Notes in Computer Science, Vol. 5809. Berlin: Springer, pp. 8–22.CrossRefGoogle Scholar
Chihara, C. S. (1987). Some problems for Bayesian confirmation theory. British Journal for the Philosophy of Science, 38(4), 551–560.CrossRefGoogle Scholar
Dawid, A. P. (1982). The well-calibrated Bayesian. Journal of the American Statistical Association, 77(379), 605–610.CrossRefGoogle Scholar
Dawid, A. P. (1985). The impossibility of inductive inference. Comment on Oakes (1985). Journal of the American Statistical Association, 80(390), 340–341.Google Scholar
Earman, J. (1992). Bayes or Bust? A Critical Examination of Bayesian Confirmation Theory. A Bradford Book. Cambridge, MA: MIT Press.Google Scholar
Freund, Y., Schapire, R. E., Singer, Y., & Warmuth, M. K. (1997). Using and combining predictors that specialize. In Proceedings of the 29th Annual ACM Symposion on Theory of Computing. New York: ACM Press, pp. 334–343.Google Scholar
Gaifman, H. & Snir, M. (1982). Probabilities over rich languages, testing and randomness. Journal of Symbolic Logic, 47(3), 495–548.CrossRefGoogle Scholar
Gelman, A. & Shalizi, C. R. (2013). Philosophy and the practice of Bayesian statistics. British Journal of Mathematical and Statistical Psychology, 66, 8–38.CrossRefGoogle ScholarPubMed
Gillies, D. A. (2001). Bayesianism and the fixity of the theoretical framework. In Corfield, D. and Williamson, J., editors, Foundations of Bayesianism. Applied Logic Series, Vol. 24. Dordrecht: Springer, pp. 363–379.CrossRefGoogle Scholar
Glymour, C. (2016). Responses to the contributions to the special issue “Causation, probability, and truth: The philosophy of Clark Glymour”. Synthese, 193(4), 1251–1285.CrossRefGoogle Scholar
Howson, C. (1988). On the consistency of Jeffreys’s simplicity postulate, and its role in Bayesian inference. The Philosophical Quarterly, 38(150), 68–83.CrossRefGoogle Scholar
Howson, C. (2000). Hume’s Problem: Induction and the Justification of Belief. New York: Oxford University Press.CrossRefGoogle Scholar
Huttegger, S. M. (2015). Merging of opinions and probability kinematics. Review of Symbolic Logic, 8(4), 611–648.CrossRefGoogle Scholar
Jeffreys, H. (1961). Theory of Probability (third edition). Oxford: Oxford University Press.Google Scholar
Kalai, E. & Lehrer, E. (1993). Rational learning leads to Nash equilibrium. Econometrica 61(5), 1019–1045.CrossRefGoogle Scholar
Kalai, E. & Lehrer, E. (1994). Weak and strong merging of opinions. Journal of Mathematical Economics, 23(1), 73–86.CrossRefGoogle Scholar
Koolen, W. M., Adamskiy, D. & Warmuth, M. K. (2012). Putting Bayes to sleep. In Pereira, F., Burges, C. J. C., Bottou, L., and Weinberger, K. Q., editors. Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., pp. 135–143.Google Scholar
Lehrer, E. & Smorodinsky, R. (1996). Merging and learning. In Ferguson, T. S., Shapley, L. S., and MacQueen, J. B., editors. Statistics, Probability and Game Theory: Papers in Honor of David Blackwell. Lecture Notes—Monograph Series, Vol. 30. Hayward, CA: Institute of Mathematical Statistics, pp. 147–168.CrossRefGoogle Scholar
Leike, J. (2016). Nonparametric General Reinforcement Learning. PhD Dissertation, Australian National University.Google Scholar
Lindley, D. V. (1982). Comment on Dawid (1982). Journal of the American Statistical Association, 77(379), 611–612.CrossRefGoogle Scholar
Lindley, D. V. (2000). The philosophy of statistics. Journal of the Royal Statistical Society: Series D (The Statistician), 49(3), 293–337.CrossRefGoogle Scholar
Mourtada, J. & Maillard, O.-A. (2017). Efficient tracking of a growing number of experts. In Hanneke, S. and Reyzin, L., editors. Proceedings of the 28th International Conference on Algorithmic Learning Theory. Proceedings of Machine Learning Research, Vol. 76. PMLR, pp. 517–539.Google Scholar
Oakes, D. (1985). Self-calibrating priors do not exist. Journal of the American Statistical Association, 80(390), 339.CrossRefGoogle Scholar
Putnam, H. (1963). ‘Degree of confirmation’ and inductive logic. In Schilpp, P. A., editor. The Philosophy of Rudolf Carnap. The Library of Living Philosophers, Vol. XI. LaSalle, IL: Open Court, pp. 761–783.Google Scholar
Raidl, E. (2020). Open-minded orthodox Bayesianism by epsilon-conditionalization. British Journal for the Philosophy of Science, 71(1), 139–176.CrossRefGoogle Scholar
Romeijn, J.-W. (2004). Hypotheses and inductive predictions. Synthese, 141(3), 333–364.Google Scholar
Romeijn, J.-W. (2005). Theory change and Bayesian statistical inference. Philosophy of Science, 72(5), 1174–1186.CrossRefGoogle Scholar
Shimony, A. (1969). Letter to Rudolf Carnap, September 20. Rudolf Carnap Papers, 1905–1970, ASP.1974.01, Series XII. Notes and Correspondence: Probability, Mathematics, Publishers, UCLA Administrative, and Lecture Notes, 1927–1970, Subseries 1: Probability Authors, Box 84b, Folder 55. Pittsburgh, PA: Special Collections Department, University of Pittsburgh.Google Scholar
Shimony, A. (1970). Scientific inference. In Colodny, R. G., editor. The Nature and Function of Scientific Theories: Essays in Contemporary Science and Philosophy. University of Pittsburgh Series in the Philosophy of Science, Vol. 4. Pittsburgh, PA: University of Pittsburgh Press, pp. 79–172.Google Scholar
Sprenger, J. (2020). Conditional degree of belief and Bayesian inference. Philosophy of Science, 87(2), 319–335.CrossRefGoogle Scholar
Sprenger, J. & Hartmann, S. (2019). Bayesian Philosophy of Science. Oxford: Oxford University Press.CrossRefGoogle Scholar
Sterkenburg, T. F. (2019). Putnam’s diagonal argument and the impossibility of a universal learning machine. Erkenntnis, 84(3), 633–656.CrossRefGoogle Scholar
Vassend, O. B. (2019). New semantics for Bayesian inference: The interpretative problem and its solutions. Philosophy of Science, 86(4), 696–718.CrossRefGoogle Scholar
Wenmackers, S. & Romeijn, J.-W. (2016). New theory about old evidence: A framework for open-minded Bayesianism. Synthese, 193(4), 1225–1250.CrossRefGoogle Scholar