Active learning using smooth relative regret approximations with applications

MaRDI QIDQ2934012zbMATH OpenFDO

Authors Nir Ailon, Ron Begleiter, Esther Ezra

Publication date 8 December 2014

Full work available at URL https://arxiv.org/abs/1110.2136, http://jmlr.csail.mit.edu/papers/v15/ailon14a.html

zbMATH Keywords

active learningclustering with side informationdisagreement coefficientlearning to rank from pairwise preferencessemi-supervised clusteringsmooth relative regret approximation

Mathematics Subject Classification ID

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

Recommendations

• Smoothness, disagreement coefficient, and the label complexity of agnostic active learning
• A compression technique for analyzing disagreement-based active learning
• Rates of convergence in active learning
• Active Learning in the Non-realizable Case
• Active learning via perfect selective classification

Cited in

(7)

• SALSAS: sub-linear active learning strategy with approximate \(k\)-NN search
• Nuclear discrepancy for single-shot batch active learning
• scientific article; zbMATH DE number 5957325 (Why is no real title available?)
• Shattering, graph orientations, and connectivity
• The relationship between agnostic selective classification, active learning and the disagreement coefficient
• Minimax robust active learning for approximately specified regression models
• Smoothness, disagreement coefficient, and the label complexity of agnostic active learning

This page was built for publication: Active learning using smooth relative regret approximations with applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2934012)