Classification with asymmetric label noise: consistency and maximal denoising

DOI10.1214/16-EJS1193zbMath1347.62106arXiv1303.1208OpenAlexW2963314381MaRDI QIDQ315419

Gilles Blanchard, Marek Flaska, Clayton Scott, Sara Pozzi, Gregory A. Handy

Publication date: 21 September 2016

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1303.1208

zbMATH Keywords

classificationconsistencylabel noisemixture proportion estimationsurrogate loss

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Pattern recognition, speech recognition (68T10)

Related Items

Binary classification with corrupted labels, Learning from binary labels with instance-dependent noise, Corrigendum to: ``Classification with asymmetric label noise: consistency and maximal denoising, Classification with asymmetric label noise: consistency and maximal denoising, Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric, Estimating the class prior for positive and unlabelled data via logistic regression, Asymmetric Error Control Under Imperfect Supervision: A Label-Noise-Adjusted Neyman–Pearson Umbrella Algorithm, Positive-unlabeled classification under class-prior shift: a prior-invariant approach based on density ratio estimation, Unnamed Item, Classification trees with mismeasured responses, Classification with label noise: a Markov chain sampling framework, On the noise estimation statistics, Harmless label noise and informative soft-labels in supervised classification, Unnamed Item, Unnamed Item, Boosting in the Presence of Outliers: Adaptive Classification With Nonconvex Loss Functions, Adaptive transfer learning, Learning from positive and unlabeled data: a survey, Unnamed Item

Cites Work

• Classification with asymmetric label noise: consistency and maximal denoising
• Strong uniform times and finite random walks
• Calibrated asymmetric surrogate losses
• Random classification noise defeats all convex potential boosters
• Robust supervised classification with mixture models: learning from data with uncertain labels
• Noise-tolerant distribution-free learning of general geometric concepts
• Support Vector Machines
• Efficient noise-tolerant learning from statistical queries
• Convexity, Classification, and Risk Bounds
• Boosting in the presence of noise
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item