Publication:4558567

zbMath1473.68174MaRDI QIDQ4558567

Robert C. Williamson, Brendan van Rooyen

Publication date: 22 November 2018

Full work available at URL: http://jmlr.csail.mit.edu/papers/v18/16-315.html

zbMATH Keywords

noise; decision theory; supervised learning; data processing; minimax bounds; generalized supervision

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

62G05: Nonparametric estimation

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, Binary classification with corrupted labels, Transfer learning for nonparametric classification: minimax rate and adaptive classifier, Improving deep label noise learning with dual active label correction

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Classification with asymmetric label noise: consistency and maximal denoising
• Convexity and well-posed problems
• Risk bounds for statistical learning
• The geometry of proper scoring rules
• Fast learning rates for plug-in classifiers
• Relative entropy under mappings by stochastic matrices
• Information-theoretic determination of minimax rates of convergence
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• Support-vector networks
• Empirical minimization
• Efficient noise-tolerant learning from statistical queries
• Support Vector Machines
• Information-theoretic upper and lower bounds for statistical estimation
• A discriminative model for semi-supervised learning
• Covering numbers for real-valued function classes
• Conditioning as disintegration
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• Lower Bounds for the Minimax Risk Using $f$-Divergences, and Applications
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Sufficiency and Approximate Sufficiency
• Discrete-Variable Extremum Problems
• Information, Divergence and Risk for Binary Experiments
• Prediction, Learning, and Games
• Uncertainty, Information, and Sequential Experiments
• Convexity, Classification, and Risk Bounds