On semimeasures predicting Martin-Löf random sequences

DOI10.1016/j.tcs.2007.03.040zbMath1127.68041arXiv0708.2319OpenAlexW2148079860WikidataQ58012416 ScholiaQ58012416MaRDI QIDQ2381581

Marcus Hutter, Andrej A. Muchnik

Publication date: 18 September 2007

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

Full work available at URL: https://arxiv.org/abs/0708.2319

zbMATH Keywords

algorithmic information theorysupermartingalesMartin-Löf randomnesssequence predictionmixture distributionsquasimeasurespredictive convergenceuniversal enumerable semimeasure

Mathematics Subject Classification ID

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

Related Items (4)

Open problems in universal induction \& intelligence ⋮ On Martin-Löf Convergence of Solomonoff’s Mixture ⋮ On the ideal convergence of sequences of fuzzy numbers ⋮ On Martin-Löf (non-)convergence of Solomonoff's universal mixture

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• HIERARCHIES OF GENERALIZED KOLMOGOROV COMPLEXITIES AND NONENUMERABLE UNIVERSAL MEASURES COMPUTABLE IN THE LIMIT
• Convergence and loss bounds for bayesian sequence prediction
• Complexity-based induction systems: Comparisons and convergence theorems
• Minimum description length induction, Bayesianism, and Kolmogorov complexity
• 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
• The definition of random sequences
• A formal theory of inductive inference. Part I
• Algorithmic Learning Theory
• Kolmogorov entropy in the context of computability theory

This page was built for publication: On semimeasures predicting Martin-Löf random sequences