Hierarchical two-part MDL code for multinomial distributions

DOI10.1016/j.ijar.2018.09.002zbMath1455.94079OpenAlexW2891666115MaRDI QIDQ1726276

Marc Boullé

Publication date: 20 February 2019

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ijar.2018.09.002

zbMATH Keywords

model selectioninformation theorydensity estimationminimum description lengthmultinomial distributionnormalized maximum likelihood

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Density estimation (62G07) Data encryption (aspects in computer science) (68P25) Measures of information, entropy (94A17) Source coding (94A29)

Uses Software

• UCI-ml
• GraphScope

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Functional data clustering via piecewise constant nonparametric density estimation
• A universal prior for integers and estimation by minimum description length
• Modeling by shortest data description
• On asymptotics of certain recurrences arising in universal coding
• Learning Bayesian network parameters from small data sets: a further constrained qualitatively maximum a posteriori method
• Consistency of data-driven histogram methods for density estimation and classification
• A linear-time algorithm for computing the multinomial stochastic complexity
• Model Selection and the Principle of Minimum Description Length
• Minimum description length induction, Bayesianism, and Kolmogorov complexity
• Strong optimality of the normalized ML models as universal codes and information in data
• Fisher information and stochastic complexity
• A Bayes Evaluation Criterion for Decision Trees
• Multivariate Density Estimation

This page was built for publication: Hierarchical two-part MDL code for multinomial distributions