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...
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the -adapted-dimension, which...
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...
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, ...
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 ...