On universal prediction and Bayesian confirmation

DOI10.1016/j.tcs.2007.05.016zbMath1124.68048arXiv0709.1516OpenAlexW2145750280WikidataQ58012418 ScholiaQ58012418MaRDI QIDQ2382281

Marcus Hutter

Publication date: 28 September 2007

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

Full work available at URL: https://arxiv.org/abs/0709.1516

zbMATH Keywords

BayesKolmogorov complexityconfirmation theoryOccam's razormodel classesblack raven paradoxphilosophical issuesSolomonoff priorsymmetry principlereparametrization invariancenoncomputable environmentsold-evidence/updating problemprediction boundsSequence prediction

Mathematics Subject Classification ID

Computational learning theory (68Q32) Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30)

Related Items (11)

Open problems in universal induction \& intelligence ⋮ A complete theory of everything (will be subjective) ⋮ A philosophical treatise of universal induction ⋮ A generalized characterization of algorithmic probability ⋮ Absolutely no free lunches! ⋮ Practical robust estimators for the imprecise Dirichlet model ⋮ On Martin-Löf Convergence of Solomonoff’s Mixture ⋮ Hydrozip: how hydrological knowledge can be used to improve compression of hydrological data ⋮ Putnam's diagonal argument and the impossibility of a universal learning machine ⋮ Solomonoff Induction Violates Nicod’s Criterion ⋮ On Martin-Löf (non-)convergence of Solomonoff's universal mixture

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal ordered problem solver
• On generalized computable universal priors and their convergence
• Algorithmic complexity bounds on future prediction errors
• A universal prior for integers and estimation by minimum description length
• On the relation between descriptional complexity and algorithmic probability
• HIERARCHIES OF GENERALIZED KOLMOGOROV COMPLEXITIES AND NONENUMERABLE UNIVERSAL MEASURES COMPUTABLE IN THE LIMIT
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Information-theoretic asymptotics of Bayes methods
• Clustering by Compression
• Convergence and loss bounds for bayesian sequence prediction
• A Theory of Program Size Formally Identical to Information Theory
• On the Complexity of Finite Sequences
• Complexity-based induction systems: Comparisons and convergence theorems
• The Selection of Prior Distributions by Formal Rules
• Laplace's law of succession and universal encoding
• Universal prediction
• 10.1162/1532443041827952
• Algorithmic Learning Theory
• Algorithmic Learning Theory
• 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
• An invariant form for the prior probability in estimation problems
• Algorithmic Learning Theory
• Theory and Applications of Models of Computation
• New error bounds for Solomonoff prediction

This page was built for publication: On universal prediction and Bayesian confirmation