Abstract

Solomonoff unified Occam's razor and Epicurus' principle of multiple explanations to one elegant, formal, universal theory of inductive inference, which initiated the field of algorithmic information theory. His central result is that the posterior of his universal semimeasure M converges rapidly to the true sequence generating posterior μ, if the latter is computable. Hence, M is eligible as a universal predictor in case of unknown μ. We investigate the existence and convergence of computable universal (semi)measures for a hierarchy of computability classes: finitely computable, estimable, enumerable, and approximable. For instance, M is known...

Citations

1412	An Introduction to Kolmogorov Complexity and Its Applications - Li, Vitanyi - 1997
138	The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms - Zvonkin, Levin - 1970
133	Zufälligkeit und Wahrscheinlichkeit - Schnorr - 1971
108	Complexity-Based Induction Systems: Comparisons and Convergence Theorems - Solomonoff - 1978
91	On the notion of a random sequence - Levin - 1973
60	Minimum Description Length Induction, bayesianism, and Kolmogorov complexity - Vitányi, Li - 1996
55	Random sequences - Lambalgen - 1987
37	A formal theory of inductive inference. part 1 & 2 - Solomonoff - 1964
30	Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit - Schmidhuber
28	Randomness and Complexity - Wang - 1996
19	Convergence and error bounds of universal prediction for general alphabet - Hutter - 2001
17	Complexity-based induction systems: Comparisons and convergence theorems - Solomono↵ - 1978
13	Sequence prediction based on monotone complexity, in - Hutter - 2003
8	A formal theory of inductive inference: Part 1 and 2 - Solomono - 1964
2	On a randomness criterion. DOKLADY: Russian Academy of Sciences Doklady - Vovk - 1987