A theory of learning with corrupted labels
From MaRDI portal
Recommendations
Cites work
- A discriminative model for semi-supervised learning
- Classification with asymmetric label noise: consistency and maximal denoising
- Conditioning as disintegration
- Convexity and well-posed problems
- Convexity, Classification, and Risk Bounds
- Covering numbers for real-valued function classes
- Discrete-variable extremum problems
- Efficient noise-tolerant learning from statistical queries
- Empirical minimization
- Estimating labels from label proportions
- Fast learning rates for plug-in classifiers
- Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
- scientific article; zbMATH DE number 3761167 (Why is no real title available?)
- scientific article; zbMATH DE number 49097 (Why is no real title available?)
- scientific article; zbMATH DE number 1207031 (Why is no real title available?)
- scientific article; zbMATH DE number 1022519 (Why is no real title available?)
- scientific article; zbMATH DE number 1064667 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 3322635 (Why is no real title available?)
- scientific article; zbMATH DE number 3068103 (Why is no real title available?)
- Information, divergence and risk for binary experiments
- Information-theoretic determination of minimax rates of convergence
- Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
- Information-theoretic upper and lower bounds for statistical estimation
- Learning from multiple sources
- Learning from partial labels
- Lower Bounds for the Minimax Risk Using f-Divergences, and Applications
- Matrix mathematics. Theory, facts, and formulas
- Prediction, Learning, and Games
- Relative entropy under mappings by stochastic matrices
- Risk bounds for statistical learning
- Statistical analysis of some multi-category large margin classification methods
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Sufficiency and Approximate Sufficiency
- Support Vector Machines
- Support-vector networks
- The geometry of proper scoring rules
- Theory of games and economic behavior.
- Uncertainty, Information, and Sequential Experiments
Cited in
(17)- Learning to classify with missing and corrupted features
- Binary classification with corrupted labels
- On biased random walks, corrupted intervals, and learning under adversarial design
- On the noise estimation statistics
- Transfer learning for nonparametric classification: minimax rate and adaptive classifier
- A non-intrusive correction algorithm for classification problems with corrupted data
- Improving deep label noise learning with dual active label correction
- scientific article; zbMATH DE number 6612702 (Why is no real title available?)
- Decontamination of mutual contamination models
- Learning from untrusted data
- Domain generalization by marginal transfer learning
- A general framework for adversarial label learning
- Dual-granularity sinkhorn distillation for enhanced learning from long-tailed noisy data
- A unified view of forward and backward losses for learning from weak labels
- NT-FAN: a simple yet effective noise-tolerant few-shot adaptation network
- A generalized Neyman-Pearson criterion for optimal domain adaptation
- Geometry and stability of supervised learning problems
This page was built for publication: A theory of learning with corrupted labels
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558567)
