Conjugate relation between loss functions and uncertainty sets in classification problems

MaRDI QIDQ2933849zbMATH OpenFDO

Authors Takafumi Kanamori, Akiko Takeda, Taiji Suzuki

Publication date 8 December 2014

Full work available at URL https://arxiv.org/abs/1204.6583, http://jmlr.csail.mit.edu/papers/v14/kanamori13a.html

zbMATH Keywords

consistencyloss functionuncertainty setconvex conjugate

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Recommendations

• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Composite binary losses
• Classification with a reject option using a hinge loss
• Classification methods with reject option based on convex risk minimization
• Chance constrained uncertain classification via robust optimization

Cited in

(4)

• Analysis to Neyman-Pearson classification with convex loss function
• An analysis on the relationship between uncertainty and misclassification rate of classifiers
• Using financial risk measures for analyzing generalization performance of machine learning models
• Support vector machines based on convex risk functions and general norms

This page was built for publication: Conjugate relation between loss functions and uncertainty sets in classification problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2933849)