Multi-View Active Learning in the Non-Realizable Case

Abstract

The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the non-realizable case under multi-view setting. We prove that, with unbounded Tsybakov noise, the sample complexity of multi-view active learning can be O( 1), contrasting to single-view setting where the polynomial improvement is the best possible achievement. We also prove that in general multi-view setting the sample complexity of active learning with unbounded Tsybakov noise is O(1), where the order of 1/ is independent of the parameter in Tsybakov noise, contrasting to previous polynomial bounds where the order of 1/ is related to the parameter in Tsybakov noise.

Tasks

Reproductions