Coping with Active Learning with Model Selection Dilemma: Minimizing Expected Generalization Error
Neil Rubens, Masashi Sugiyama · 2006
Optimally designing the location of training input points (active learning) and choosing the best model (model selection) are two important ingredients of supervised learning and have been studied extensively. However, these two issues seem to have been investigated separately as two independent problems. If training input points and models are simultaneously optimized, the generalization performance would be further improved. In this paper, we therefore propose a new approach called ensemble active learning for solving the problems of active learning and model selection at the same time. We demonstrate by the numerical experiments with toy and benchmark data sets that the proposed approach compares favorably with alternative methods.