Density estimation by stochastic complexity

DOI10.1109/18.119689MaRDI QIDQ3990767zbMATH OpenOpenAlexFDO

Authors Jorma Rissanen, Bin Yu, Terence P. Speed

Publication date 28 June 1992

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

Full work available at URL https://doi.org/10.1109/18.119689

zbMATH Keywords

asymptotic boundscode redundancydynamic programmingequal bin widthsgeneralized histogram estimatorsMDL principleminimum description length principleoptimization of histogram density estimatorsstochastic complexityunequal bin widthsuniversal coding theoremsvariable bin widths

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Density estimation (62G07) Coding theorems (Shannon theory) (94A24)

Recommendations

• Stochastic complexity, histograms and hypothesis testing of homogeneity
• On stochastic complexity and nonparametric density estimation
• Data compression and histograms
• On stochastic complexity estimation: a decision-theoretic approach
• scientific article; zbMATH DE number 1859209

Cited in

(24)

• Data compression and histograms
• Toward efficient agnostic learning
• Mutual information, metric entropy and cumulative relative entropy risk
• Information-theoretic determination of minimax rates of convergence
• Using the minimum description length to discover the intrinsic cardinality and dimensionality of time series
• Test for homogeneity of several populations by stochastic complexity
• Combining regular and irregular histograms by penalized likelihood
• Accumulative prediction error and the selection of time series models
• Predictability, complexity, and learning
• Information optimality and Bayesian modelling
• On stochastic complexity and nonparametric density estimation
• On stochastic complexity estimation: a decision-theoretic approach
• Convergence rates for the minimum complexity estimator of counting process intensities^∗
• Catching up Faster by Switching Sooner: A Predictive Approach to Adaptive Estimation with an Application to the AIC–BIC Dilemma
• Learning Theory
• An Introduction to Coding Theory and the Two-Part Minimum Description Length Principle
• Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection
• Data driven versions of pearson's chisquare test for uniformity
• Stochastic complexity, histograms and hypothesis testing of homogeneity
• Fluctuation-Dissipation Theorem and Models of Learning
• A comparison of automatic histogram constructions
• Fast and fully-automated histograms for large-scale data sets
• Clustgrams: an extension to histogram densities based on the minimum description length principle
• Mint: MDL-based approach for mining interesting numerical pattern sets

This page was built for publication: Density estimation by stochastic complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3990767)