New error bounds for Solomonoff prediction

DOI10.1006/jcss.2000.1743zbMath0983.68083arXivcs/9912008OpenAlexW2124741838MaRDI QIDQ5946059

Marcus Hutter

Publication date: 21 April 2002

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/cs/9912008

zbMATH Keywords

Solomonoff sequence prediction

Mathematics Subject Classification ID

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

Related Items (9)

On universal prediction and Bayesian confirmation ⋮ Algorithmic complexity bounds on future prediction errors ⋮ Open problems in universal induction \& intelligence ⋮ On the computability of Solomonoff induction and AIXI ⋮ HIERARCHIES OF GENERALIZED KOLMOGOROV COMPLEXITIES AND NONENUMERABLE UNIVERSAL MEASURES COMPUTABLE IN THE LIMIT ⋮ On calibration error of randomized forecasting algorithms ⋮ Solomonoff Induction Violates Nicod’s Criterion ⋮ On the Computability of Solomonoff Induction and Knowledge-Seeking ⋮ Sequential predictions based on algorithmic complexity

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Inductive reasoning and Kolmogorov complexity
• The discovery of algorithmic probability
• Complexity-based induction systems: Comparisons and convergence theorems
• THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS
• Computational Complexity and Probability Constructions
• A formal theory of inductive inference. Part I

This page was built for publication: New error bounds for Solomonoff prediction