• Computer Science, Mathematics
  • Published in NIPS 2010

Multi-View Active Learning in the Non-Realizable Case

@inproceedings{Wang2010MultiViewAL,
  title={Multi-View Active Learning in the Non-Realizable Case},
  author={Wei Wang and Zhi-Hua Zhou},
  booktitle={NIPS},
  year={2010}
}
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(log 1/e), contrasting to single-view setting where the polynomial improvement is the best… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS