Predictor-rejector multi-class abstention: theoretical analysis and algorithms

MaRDI QIDQ7017082zbMATH OpenFDO

Authors Anqi Mao, Mehryar Mohri, Yutao Zhong

Publication date 6 March 2025

Full work available at URL https://proceedings.mlr.press/v237/mao24a.html

zbMATH Keywords

abstentionconsistencylearning theory

Mathematics Subject Classification ID

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

Cites work

• A compression technique for analyzing disagreement-based active learning
• Active learning via perfect selective classification
• Agnostic pointwise-competitive selective classification
• Classification methods with reject option based on convex risk minimization
• Classification with a reject option using a hinge loss
• Classification with reject option
• Composite binary losses
• Consistent algorithms for multiclass classification with an abstain option
• How to compare different loss functions and their risks
• scientific article; zbMATH DE number 1759592 (Why is no real title available?)
• scientific article; zbMATH DE number 2089926 (Why is no real title available?)
• Learning with Rejection
• Multicategory Support Vector Machines
• On optimum recognition error and reject tradeoff
• On the foundations of noise-free selective classification

Cited in

(1)

• A connection between learning to reject and Bhattacharyya divergences

This page was built for publication: Predictor-rejector multi-class abstention: theoretical analysis and algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017082)