Sciweavers

Share
COLT
2010
Springer

Robust Selective Sampling from Single and Multiple Teachers

9 years 14 days ago
Robust Selective Sampling from Single and Multiple Teachers
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of our algorithm and on the number of labels it queries when faced with an adaptive adversarial strategy of generating the instances. Our bounds both generalize and strictly improve over previous bounds in similar settings. Using a simple online-to-batch conversion technique, our selective sampling algorithm can be converted into a statistical (pool-based) active learning algorithm. We extend our algorithm and analysis to the multiple-teacher setting, where the algorithm can choose which subset of teachers to query for each label.
Ofer Dekel, Claudio Gentile, Karthik Sridharan
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where COLT
Authors Ofer Dekel, Claudio Gentile, Karthik Sridharan
Comments (0)
books