65 search results - page 4 / 13 » A bound on the label complexity of agnostic active learning |
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We propose an importance weighting framework for actively labeling samples. This technique yields practical yet sound active learning algorithms for general loss functions. Experi...
JMLR
2010
13 years 2 months ago
2010
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 ...
COLT
2008
Springer
13 years 9 months ago
2008
Springer
We describe and explore a new perspective on the sample complexity of active learning. In many situations where it was generally believed that active learning does not help, we sh...
ALT
1998
Springer
13 years 11 months ago
1998
Springer
Exact learning of half-spaces over finite subsets of IRn from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from ...
COLT
2010
Springer
13 years 5 months ago
2010
Springer
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...