Learning with a Drifting Target Concept

@inproceedings{Hanneke2015LearningWA,
  title={Learning with a Drifting Target Concept},
  author={Steve Hanneke and Varun Kanade and Liu Yang},
  booktitle={ALT},
  year={2015}
}
We study the problem of learning in the presence of a drifting target concept. Specifically, we provide bounds on the error rate at a given time, given a learner with access to a history of independent samples labeled according to a target concept that can change on each round. One of our main contributions is a refinement of the best previous results for polynomial-time algorithms for the space of linear separators under a uniform distribution. We also provide general results for an algorithm… CONTINUE READING
BETA

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-5 OF 5 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-9 OF 9 REFERENCES

Analysis of perceptron - based active learning

Y. Mansour, E. Even-Dar, J. Wortman Vaughan, A. Kalai Dasgupta, C. Monteleoni
  • Concentration Inequalities
  • 2013

Helmbold

P. L. Bartlett, P D.
  • Learning changing problems,
  • 1996

On the complexity of learning from drifting distributions

G. Lugosi, P. Massart
  • Inf . Comput .

Similar Papers

Loading similar papers…