Sciweavers

46 search results - page 1 / 10
» The True Sample Complexity of Active Learning
Sort
View
COLT
2008
Springer
13 years 6 months ago
The True Sample Complexity of Active Learning
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...
Maria-Florina Balcan, Steve Hanneke, Jennifer Wort...
CORR
2010
Springer
94views Education» more  CORR 2010»
13 years 5 months ago
Tight Sample Complexity of Large-Margin Learning
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the -adapted-dimension, which...
Sivan Sabato, Nathan Srebro, Naftali Tishby
ICML
2006
IEEE
14 years 5 months ago
Agnostic active learning
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...
Maria-Florina Balcan, Alina Beygelzimer, John Lang...
CORR
2010
Springer
116views Education» more  CORR 2010»
13 years 5 months ago
Multi-View Active Learning in the Non-Realizable Case
The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, ...
Wei Wang, Zhi-Hua Zhou
JMLR
2010
143views more  JMLR 2010»
12 years 11 months ago
Rademacher Complexities and Bounding the Excess Risk in Active Learning
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 ...
Vladimir Koltchinskii