Active and passive learning of linear separators under log-concave distributions

@inproceedings{Balcan2013ActiveAP,
  title={Active and passive learning of linear separators under log-concave distributions},
  author={Maria-Florina Balcan and Philip M. Long},
  booktitle={COLT},
  year={2013}
}
We provide new results concerning label efficient, polynomial time, passive and active learning of linear separators. We prove that active learning provides an exponential improvement over PAC (passive) learning of homogeneous linear separators under nearly log-concave distributions. Building on this, we provide a computationally efficient PAC algorithm with optimal (up to a constant factor) sample complexity for such problems. This resolves an open question of (Long, 1995, 2003; Bshouty et al… CONTINUE READING
Highly Cited
This paper has 84 citations. REVIEW CITATIONS

Topics

Statistics

02040201320142015201620172018
Citations per Year

84 Citations

Semantic Scholar estimates that this publication has 84 citations based on the available data.

See our FAQ for additional information.