CMU-ML-07-103
Machine Learning Department
School of Computer Science, Carnegie Mellon University


CMU-ML-07-103

A Bound on the Label Complexity
of Agnostic Active Learning

Steve Hanneke

March 2007

CMU-ML-07-103.pdf


Keywords: Agnostic active learning, label complexity, PAC


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

10 pages

SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu