Minimax Analysis of Active Learning
JOURNAL OF MACHINE LEARNING RESEARCH, pp. 3487.0-3602.0, 2015.
This work establishes distribution-free upper and lower bounds on the minimax label complexity of active learning with general hypothesis classes, under various noise models. The results reveal a number of surprising facts. In particular, under the noise model of Tsybakov (2004), the minimax label complexity of active learning with a VC c...More
PPT (Upload PPT)