Minimax semi-supervised set-valued approach to multi-class classification

DOI10.3150/20-BEJ1313zbMath1473.62407OpenAlexW3195780253MaRDI QIDQ1983613

Evgenii Chzhen, Christophe Denis, Mohamed Hebiri

Publication date: 10 September 2021

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3150/20-bej1313

zbMATH Keywords

multi-class classificationminimax optimalitysemi-supervised classificationset-valued classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Minimax procedures in statistical decision theory (62C20) Learning and adaptive systems in artificial intelligence (68T05) Topological data analysis (62R40)

Related Items (2)

Minimax semi-supervised set-valued approach to multi-class classification ⋮ Optimal rates for nonparametric F-score binary classification via post-processing

Uses Software

• Scikit
• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule
• Optimal rates for plug-in estimators of density level sets
• Risk bounds for statistical learning
• Fast learning rates for plug-in classifiers
• Robust reconstruction of functions by the local-approximation method
• Consistent nonparametric regression. Discussion
• On nonparametric estimation of density level sets
• Smooth discrimination analysis
• On the prediction loss of the Lasso in the partially labeled setting
• Optimal global rates of convergence for nonparametric regression
• A distribution-free theory of nonparametric regression
• Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
• Minimax semi-supervised set-valued approach to multi-class classification
• Minimax optimal rates for Mondrian trees and forests
• Hopf bifurcation analysis and numerical simulations in an ODE model of the immune system with positive immune response
• Comments on: ``A random forest guided tour
• Classification with confidence
• A New Lower Bound for Multiple Hypothesis Testing
• Estimation of a Convex Density Contour in Two Dimensions
• Minimax nonparametric classification .I. Rates of convergence
• Confidence sets with expected sizes for Multiclass Classification
• Least Ambiguous Set-Valued Classifiers With Bounded Error Levels
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Classification with reject option
• Random forests

This page was built for publication: Minimax semi-supervised set-valued approach to multi-class classification