A bound on the label complexity of agnostic active learning

Key Points

Key points are not available for this paper at this time.

Abstract

We study the label complexity of pool-based active learning in the agnostic PAC model. Specifically, we derive general bounds on the number of label requests made by the A2 algorithm proposed by Balcan, Beygelzimer & Langford (Balcan et al., 2006). This represents the first nontrivial general-purpose upper bound on label complexity in the agnostic PAC model.

Bookmark

Cite This Study

Steve Hanneke (Wed,) studied this question.

synapsesocial.com/papers/6a0fb9834fb650da4ffe714e https://doi.org/https://doi.org/10.1145/1273496.1273541

Bookmark