scientific article; zbMATH DE number 6982911

zbMath1467.68151MaRDI QIDQ4558475

Ambuj Tewari, Pradeep Ravikumar, Nagarajan Natarajan, Inderjit S. Dhillon

Publication date: 22 November 2018

Full work available at URL: http://jmlr.csail.mit.edu/papers/v18/15-226.html

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

statistical consistencycost-sensitive learningclass-conditional label noise

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)

Related Items (21)

Regularization via Mass Transportation ⋮ Binary classification with corrupted labels ⋮ Learning from binary labels with instance-dependent noise ⋮ Corrigendum to: ``Classification with asymmetric label noise: consistency and maximal denoising ⋮ An iterative algorithm to learn from positive and unlabeled examples ⋮ Joint feature selection and classification for positive unlabelled multi-label data using weighted penalized empirical risk minimization ⋮ A non-intrusive correction algorithm for classification problems with corrupted data ⋮ Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric ⋮ Improving deep label noise learning with dual active label correction ⋮ Estimating the class prior for positive and unlabelled data via logistic regression ⋮ How to handle noisy labels for robust learning from uncertainty ⋮ Unnamed Item ⋮ Millionaire: a hint-guided approach for crowdsourcing ⋮ An instance-dependent simulation framework for learning with label noise ⋮ Instance weighting through data imprecisiation ⋮ Confident Learning: Estimating Uncertainty in Dataset Labels ⋮ Learning from positive and unlabeled data: a survey ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Towards harnessing feature embedding for robust learning with noisy labels

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Classification with asymmetric label noise: consistency and maximal denoising
• Adaptive regularization of weight vectors
• Calibrated asymmetric surrogate losses
• Random classification noise defeats all convex potential boosters
• Sample-efficient strategies for learning in the presence of noise
• Learning Kernel Perceptrons on Noisy Data Using Random Projections
• What Shape Is Your Conjugate? A Survey of Computational Convex Analysis and Its Applications
• Robust Stochastic Approximation Approach to Stochastic Programming
• Online Learning of Noisy Data
• Understanding Machine Learning
• Convexity, Classification, and Risk Bounds

This page was built for publication: