Model Selection and Error Estimation
Machine Learning
Journal of Computer and System Sciences
Importance weighted active learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Rademacher penalties and structural risk minimization
IEEE Transactions on Information Theory
Minimax Bounds for Active Learning
IEEE Transactions on Information Theory
Smoothness, Disagreement Coefficient, and the Label Complexity of Agnostic Active Learning
The Journal of Machine Learning Research
Plug-in approach to active learning
The Journal of Machine Learning Research
Activized learning: transforming passive to active with improved label complexity
The Journal of Machine Learning Research
A theory of transfer learning with applications to active learning
Machine Learning
Selective sampling and active learning from single and multiple teachers
The Journal of Machine Learning Research
Hi-index | 0.00 |
Sequential algorithms of active learning based on the estimation of the level sets of the empirical risk are discussed in the paper. Localized Rademacher complexities are used in the algorithms to estimate the sample sizes needed to achieve the required accuracy of learning in an adaptive way. Probabilistic bounds on the number of active examples have been proved and several applications to binary classification problems are considered.