Minimum description length induction, Bayesianism, and Kolmogorov complexity

DOI10.1109/18.825807MaRDI QIDQ4503537zbMATH OpenOpenAlexFDO

Authors 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)

Recommendations

• Model selection based on minimum description length
• Model Selection and the Principle of Minimum Description Length
• Minimum Message Length and Kolmogorov Complexity
• The minimum description length principle in coding and modeling
• Information and complexity in statistical modeling.

Cited in

(43)

• The miraculous universal distribution
• Learning about the parameter of the Bernoulli model
• The generalized universal law of generalization.
• Applying MDL to learn best model granularity
• Hierarchical two-part MDL code for multinomial distributions
• 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
• 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
• Sequential predictions based on algorithmic complexity
• Predictability, complexity, and learning
• Bayes factors, relations to minimum description length, and overlapping model classes
• THE FASTEST AND SHORTEST ALGORITHM FOR ALL WELL-DEFINED PROBLEMS
• Using MDL for Grammar Induction
• Exact Minimax Strategies for Predictive Density Estimation, Data Compression, and Model Selection
• Asymptotics of Discrete MDL for Online Prediction
• An information-geometric approach to learning Bayesian network topologies from data
• Computable Bayesian compression for uniformly discretizable statistical models
• scientific article; zbMATH DE number 740676 (Why is no real title available?)
• Characterization of the Bayes estimator and the MDL estimator for exponential families
• Counting probability distributions: Differential geometry and model selection
• An analysis of the difference of code lengths between two-step codes based on MDL principle and Bayes codes
• Textual data compression in computational biology: algorithmic techniques
• scientific article; zbMATH DE number 940830 (Why is no real title available?)
• On Different Facets of Regularization Theory
• Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection
• A revision of coding theory for learning from language
• Minimum Message Length and Kolmogorov Complexity
• Discussion of the Papers by Rissanen, and by Wallace and Dowe
• Minimum description length revisited
• Learning as Data Compression
• Bayes not Bust! Why Simplicity is no Problem for Bayesians
• scientific article; zbMATH DE number 2188025 (Why is no real title available?)
• Algorithmic Learning Theory
• Observation of Unbounded Novelty in Evolutionary Algorithms is Unknowable
• Kolmogorov's Last Discovery? (Kolmogorov and Algorithmic Statistics)
• Learning genetic population structures using minimization of stochastic complexity
• Random item response data generation using a limited-information approach: applications to assessing model complexity
• Constructing perfect steganographic systems
• MODL: a Bayes optimal discretization method for continuous attributes
• On generalized computable universal priors and their convergence

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4503537)