Multi-View Active Learning in the Non-Realizable Case

Details Multi-View Active Learning in the Non-Realizable Case Multi-View Active Learning in the Non-Realizable Case

2010-05-31

arxiv.org/abs/1005.5581v2

Computer Science

Learning

22 pages, 1 figure

Scientific paper

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 $\widetilde{O}(\log\frac{1}{\epsilon})$, 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 $\widetilde{O}(\frac{1}{\epsilon})$, where the order of $1/\epsilon$ is independent of the parameter in Tsybakov noise, contrasting to previous polynomial bounds where the order of $1/\epsilon$ is related to the parameter in Tsybakov noise.

Affiliated with

Also associated with

No associations

Rating

Multi-View Active Learning in the Non-Realizable Case does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Multi-View Active Learning in the Non-Realizable Case, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-View Active Learning in the Non-Realizable Case will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-627142