Active Learning for Binary Classification with Abstention

@article{Shekhar2019ActiveLF,
  title={Active Learning for Binary Classification with Abstention},
  author={Shubhanshu Shekhar and Mohammad Ghavamzadeh and Tara Javidi},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.00303}
}
We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two variants of \emph{bounded-rate} abstention, and for each of them propose an active learning algorithm. All the proposed algorithms can work in the most commonly used active learning models, i.e., \emph{membership-query}, \emph{pool-based}, and \emph{stream-based} sampling. We obtain upper-bounds on the excess risk of our… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Plug-in Approach to Active Learning

  • J. Mach. Learn. Res.
  • 2012
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Introduction to Nonparametric Estimation

  • Springer series in statistics
  • 2008
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

X-Armed Bandits

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Classification with a Reject Option using a Hinge Loss

  • J. Mach. Learn. Res.
  • 2008
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

A plug-in approach to neyman-pearson classification

  • J. Mach. Learn. Res.
  • 2013
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Minimax Bounds for Active Learning

  • IEEE Transactions on Information Theory
  • 2007
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…