Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure

DOI10.1109/TSP.2015.2477805zbMATH Open1412.94133DBLPjournals/tsp/BerishaWHS16OpenAlexW2218423201WikidataQ30364494 ScholiaQ30364494MaRDI QIDQ4618147FDOQ4618147

Authors: Visar Berisha, Alan Wisler, Alfred O. III Hero, Andreas Spanias 

Publication date: 7 February 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tsp.2015.2477805

Recommendations

• Divergence-based estimation and testing of statistical models of classification
• Upper-bound estimates for classifiers based on a dissimilarity function
• Divergence-based estimation and testing with misclassified data
• scientific article; zbMATH DE number 4203496
• On error-rate estimation in nonparametric classification
• On Some Nonparametric Density Estimators for a Statistical Classification Problem
• Nonparametric estimation of Kullback-Leibler divergence
• scientific article; zbMATH DE number 3917475
• Prediction Error Estimation Under Bregman Divergence for Non‐Parametric Regression and Classification

Mathematics Subject Classification ID

Measures of information, entropy (94A17)

This page was built for publication: Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4618147)