Random worlds and maximum entropy

Given a knowledge base theta containing first-order and statistical facts, a principled method, called the random-worlds method, for computing a degree of belief that some phi holds given theta is considered. If the domain has size N, then one can consider all possible worlds with domain (1, . . ., N) that satisfy theta and compute the fraction of them in which phi is true. The degree of belief is defined as the asymptotic value of this fraction as N grows large. It is shown that when the vocabulary underlying phi and theta uses constants and unary predicates only, one can in many cases use a maximum entropy computation to compute the degree of belief. Making precise exactly when a maximum entropy calculation can be used turns out to be subtle. The subtleties are explored, and sufficient conditions that cover many of the cases that occur in practice are provided.<<ETX>>

[1]  Judea Pearl,et al.  Probabilistic Semantics for Nonmonotonic Reasoning: A Survey , 1989, KR.

[2]  David J. Spiegelhalter,et al.  Probabilistic Reasoning in Predictive Expert Systems , 1985, UAI.

[3]  Joseph Y. Halpern,et al.  Asymptomatic conditional probabilities for first-order logic , 1992, STOC '92.

[4]  John L. Pollock,et al.  Foundations for direct inference , 1994 .

[5]  E. T. Jaynes,et al.  Where do we Stand on Maximum Entropy , 1979 .

[6]  Joseph Y. Halpern,et al.  From Statistics to Beliefs , 1992, AAAI.

[7]  Fahiem Bacchus,et al.  Representing and reasoning with probabilistic knowledge , 1988 .

[8]  Yu. V. Glebskii,et al.  Range and degree of realizability of formulas in the restricted predicate calculus , 1969 .

[9]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[10]  J. Keynes.  A Treatise on Probability. , 1923 .

[11]  Peter C. Cheeseman,et al.  A Method of Computing Generalized Bayesian Probability Values for Expert Systems , 1983, IJCAI.

[12]  Jeff B. Paris,et al.  On the applicability of maximum entropy to inexact reasoning , 1989, Int. J. Approx. Reason..

[13]  E. Jaynes.  On the rationale of maximum-entropy methods , 1982, Proceedings of the IEEE.

[14]  Ronald Fagin,et al.  Probabilities on finite models , 1976, Journal of Symbolic Logic.

[15]  Joseph Y. Halpern.  An Analysis of First-Order Logics of Probability , 1989, IJCAI.

[16]  W. Deming,et al.  On a Least Squares Adjustment of a Sampled Frequency Table When the Expected Marginal Totals are Known , 1940 .

[17]  R. Selten.  Reexamination of the perfectness concept for equilibrium points in extensive games , 1975, Classics in Game Theory.