Negative Results for Active Learning with Convex Losses

[edit]

Steve Hanneke, Liu Yang ;
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:321-325, 2010.

Abstract

We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no better than passive learning.

Related Material