Minimum description length induction, Bayesianism, and Kolmogorov complexity

DOI10.1109/18.825807zbMath1013.68096OpenAlexW2113832384MaRDI QIDQ4503537

Paul M. B. Vitányi, Ming Li

Publication date: 7 September 2000

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://ir.cwi.nl/pub/1198

zbMATH Keywords

data compressionminimum description lengthminimum message length

Mathematics Subject Classification ID

Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30) Communication, information (94A99)

Related Items (26)

Observation of Unbounded Novelty in Evolutionary Algorithms is Unknowable ⋮ Counting probability distributions: Differential geometry and model selection ⋮ On semimeasures predicting Martin-Löf random sequences ⋮ `Ideal learning' of natural language: positive results about learning from positive evidence ⋮ Ockham's razor, empirical complexity, and truth-finding efficiency ⋮ MODL: a Bayes optimal discretization method for continuous attributes ⋮ On Different Facets of Regularization Theory ⋮ On generalized computable universal priors and their convergence ⋮ Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection ⋮ Kolmogorov's Last Discovery? (Kolmogorov and Algorithmic Statistics) ⋮ The generalized universal law of generalization. ⋮ Learning genetic population structures using minimization of stochastic complexity ⋮ Textual data compression in computational biology: algorithmic techniques ⋮ Hierarchical two-part MDL code for multinomial distributions ⋮ An Information-Geometric Approach to Learning Bayesian Network Topologies from Data ⋮ THE FASTEST AND SHORTEST ALGORITHM FOR ALL WELL-DEFINED PROBLEMS ⋮ A Revision of Coding Theory for Learning from Language ⋮ Predictability, Complexity, and Learning ⋮ Constructing perfect steganographic systems ⋮ Application of Kolmogorov complexity and universal codes to identity testing and nonparametric testing of serial independence for time series ⋮ Compact representations as a search strategy: compression EDAs ⋮ Model selection by normalized maximum likelihood ⋮ Computable Bayesian Compression for Uniformly Discretizable Statistical Models ⋮ Minimum description length revisited ⋮ Applying MDL to learn best model granularity ⋮ Sequential predictions based on algorithmic complexity

This page was built for publication: Minimum description length induction, Bayesianism, and Kolmogorov complexity