Consistency of multiclass empirical risk minimization methods based on convex loss

zbMATH Open1222.62068MaRDI QIDQ3174045FDOQ3174045

Authors: Di-Rong Chen, Tao Sun 

Publication date: 12 October 2011

Full work available at URL: http://www.jmlr.org/papers/v7/chen06a.html

Recommendations

• Statistical behavior and consistency of classification methods based on convex risk minimization.
• On the consistency of multiclass classification methods
• On the rate of convergence for multi-category classification based on convex losses
• Convexity, Classification, and Risk Bounds
• Statistical analysis of some multi-category large margin classification methods

zbMATH Keywords

empirical risk minimizationclassifiermulticlass classificationTsybakov noise conditionconstrained comparison method

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial intelligence (68T99)

Cited In (9)

• Error analysis of multicategory support vector machine classifiers
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Universal consistency of Wasserstein k-NN classifier: a negative and some positive results
• On the rate of convergence for multi-category classification based on convex losses
• ERM learning algorithm for multi-class classification
• A Fisher consistent multiclass loss function with variable margin on positive examples
• On the consistency of multiclass classification methods
• On the consistency of multi-label learning
• Learning Theory

This page was built for publication: Consistency of multiclass empirical risk minimization methods based on convex loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174045)