A note on active learning for smooth problems

Abstract

We show that the disagreement coefficient of certain smooth hypothesis classes is $O(m)$, where $m$ is the dimension of the hypothesis space, thereby answering a question posed in \cite{friedman09}.

Cited by in corpus (2)

• Activized Learning: Transforming Passive to Active with Improved Label Complexity
• Surrogate Losses in Passive and Active Learning