On classification with empirically observed statistics and universal data compression

DOI10.1109/18.2636MaRDI QIDQ4729185zbMATH OpenOpenAlexFDO

Authors Jacob Ziv

Publication date 1988

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

Full work available at URL https://doi.org/10.1109/18.2636

zbMATH Keywords

Classificationfinite alphabet sourceslikelihood ratio discriminant functionoptimal discriminant functionStein's lemmauniversal data compressionuniversal discriminant functions

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Information theory (general) (94A15)

Recommendations

• scientific article; zbMATH DE number 826063
• Classification With Finite Memory Revisited
• Classification via Minimum Incremental Coding Length
• A measure of relative entropy between individual sequences with application to universal classification
• Classification with finite memory

Cited in

(18)

• Information-theoretic method for classification of texts
• Compression based homogeneity testing
• Joint string complexity for Markov sources: small data matters
• Application of Kolmogorov complexity and universal codes to identity testing and nonparametric testing of serial independence for time series
• Spotting neural spike patterns using an adversary background model
• scientific article; zbMATH DE number 5957476 (Why is no real title available?)
• Classification via Minimum Incremental Coding Length
• Data Compression and Selection of Variables, with Respect to Exact Inference
• A Bayesian approach for classification of Markov sources
• Compressive classification: where wireless communications meets machine learning
• Classification With Finite Memory Revisited
• A measure of relative entropy between individual sequences with application to universal classification
• Textual data compression in computational biology: algorithmic techniques
• scientific article; zbMATH DE number 826063 (Why is no real title available?)
• Classification with finite memory
• Search for sparse active inputs: a review
• Randomization of data acquisition and \(\ell_{1}\)-optimization (recognition with compression)
• Universal Neyman-Pearson classification with a partially known hypothesis

This page was built for publication: On classification with empirically observed statistics and universal data compression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4729185)