Sciweavers

Share
NIPS
2007

A general agnostic active learning algorithm

12 years 1 months ago
A general agnostic active learning algorithm
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 Cohn, Atlas, and Ladner to the agnostic setting, by (1) reformulating it using a reduction to supervised learning and (2) showing how to apply generalization bounds even for the non-i.i.d. samples that result from selective sampling. We provide a general characterization of the label complexity of our algorithm. This quantity is never more than the usual PAC sample complexity of supervised learning, and is exponentially smaller for some hypothesis classes and distributions. We also demonstrate improvements experimentally.
Sanjoy Dasgupta, Daniel Hsu, Claire Monteleoni
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2007
Where NIPS
Authors Sanjoy Dasgupta, Daniel Hsu, Claire Monteleoni
Comments (0)
books