On generalized computable universal priors and their convergence

DOI10.1016/j.tcs.2006.07.039zbMath1110.03031arXivcs/0503026WikidataQ58012433 ScholiaQ58012433MaRDI QIDQ860822

Marcus Hutter

Publication date: 9 January 2007

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/cs/0503026

zbMATH Keywords

algorithmic information theory; Martin-Löf randomness; sequence prediction; mixture distributions; posterior convergence; computability concepts; Solomonoff's prior; universal probability

Mathematics Subject Classification ID

68Q32: Computational learning theory

68Q30: Algorithmic information theory (Kolmogorov complexity, etc.)

03D80: Applications of computability and recursion theory

Related Items

On universal prediction and Bayesian confirmation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• Zufälligkeit und Wahrscheinlichkeit. Eine algorithmische Begründung der Wahrscheinlichkeitstheorie. (Randomness and probability. An algorithmic foundation of probability theory)
• HIERARCHIES OF GENERALIZED KOLMOGOROV COMPLEXITIES AND NONENUMERABLE UNIVERSAL MEASURES COMPUTABLE IN THE LIMIT
• Von Mises' definition of random sequences reconsidered
• A Theory of Program Size Formally Identical to Information Theory
• Complexity-based induction systems: Comparisons and convergence theorems
• Minimum description length induction, Bayesianism, and Kolmogorov complexity
• Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences
• Learning Theory and Kernel Machines
• Algorithmic Learning Theory
• THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS
• A formal theory of inductive inference. Part II
• Algorithmic Learning Theory