Affiliation:
1. Department of Computer Science, University of Tübingen, 72076 Tübingen, Germany
2. Department of Computer Science, University of Tübingen, Germany and Tübingen AI Center, 72076 Tübingen, Germany
Abstract
In the literature on imprecise probability, little attention is paid to the fact that imprecise probabilities are precise on a set of events. We call these sets systems of precision. We show that, under mild assumptions, the system of precision of a lower and upper probability form a so-called (pre-)Dynkin system. Interestingly, there are several settings, ranging from machine learning on partial data over frequential probability theory to quantum probability theory and decision making under uncertainty, in which, a priori, the probabilities are only desired to be precise on a specific underlying set system. Here, (pre-)Dynkin systems have been adopted as systems of precision, too. We show that, under extendability conditions, those pre-Dynkin systems equipped with probabilities can be embedded into algebras of sets. Surprisingly, the extendability conditions elaborated in a strand of work in quantum probability are equivalent to coherence from the imprecise probability literature. On this basis, we spell out a lattice duality which relates systems of precision to credal sets of probabilities. We conclude the presentation with a generalization of the framework to expectation-type counterparts of imprecise probabilities. The analogue of pre-Dynkin systems turns out to be (sets of) linear subspaces in the space of bounded, real-valued functions. We introduce partial expectations, natural generalizations of probabilities defined on pre-Dynkin systems. Again, coherence and extendability are equivalent. A related but more general lattice duality preserves the relation between systems of precision and credal sets of probabilities.
Funder
Deutsche Forschungsgemeinschaft
Subject
General Physics and Astronomy
Reference88 articles.
1. The general theory of measure and probability calculus;Kolmogorov;Collected Works of the Mathematical Section, Communist Academy, Section for Natural and Exact Sciences,1929
2. Walley, P. (1991). Statistical Reasoning with Imprecise Probabilities, Chapman and Hall.
3. Eban, E., Mezuman, E., and Globerson, A. (2014, January 21–26). Discrete Chebyshev classifiers. Proceedings of the International Conference on Machine Learning. PMLR, Beijing, China.
4. Gudder, S.P. (1979). Stochastic Methods in Quantum Mechanics, North Holland.
5. Subjective probabilities on subjectively unambiguous events;Epstein;Econometrica,2001