We propose a formulation of the Decision Tree learning algorithm in the Compression settings and derive tight generalization error bounds. In particular, we propose Sample Compres...
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, ...
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
We consider the Multi-armed bandit problem under the PAC (“probably approximately correct”) model. It was shown by Even-Dar et al. [5] that given n arms, it suffices to play th...
We present the first PAC bounds for learning parameters of Conditional Random Fields [12] with general structures over discrete and real-valued variables. Our bounds apply to com...