Predicting non-stationary processes

DOI10.1016/j.aml.2007.04.004zbMath1145.60023WikidataQ58012402 ScholiaQ58012402MaRDI QIDQ2425399

Daniil Ryabko, Marcus Hutter

Publication date: 5 May 2008

Published in: Applied Mathematics Letters (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/1885/15002

zbMATH Keywords

sequence prediction; absolute/KL divergence; average/expected criteria; local absolute continuity; mixture of measures; non-stationary measures

Mathematics Subject Classification ID

60E99: Distribution theory

60G25: Prediction theory (aspects of stochastic processes)

Related Items

Unnamed Item, On the possibility of learning in reactive environments with arbitrary dependence, Open problems in universal induction \& intelligence, Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor

Cites Work

• Unnamed Item
• On the possibility of learning in reactive environments with arbitrary dependence
• Prediction of random sequences and universal coding
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence
• Merging of Opinions with Increasing Information
• Complexity-based induction systems: Comparisons and convergence theorems
• Bayesian Representation of Stochastic Processes under Learning: de Finetti Revisited
• 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 I