Optimal and Adaptive Algorithms for Online Boosting

@inproceedings{Beygelzimer2015OptimalAA,
  title={Optimal and Adaptive Algorithms for Online Boosting},
  author={Alina Beygelzimer and Satyen Kale and Haipeng Luo},
  booktitle={IJCAI},
  year={2015}
}
We study online boosting, the task of converting any weak online learner into a strong online learner. Based on a novel and natural definition of weak online learnability, we develop two online boosting algorithms. The first algorithm is an online version of boost-by-majority. By proving a matching lower bound, we show that this algorithm is essentially optimal in terms of the number of weak learners and the sample complexity needed to achieve a specified accuracy. The second algorithm is… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 28 CITATIONS

Gradient Boosting on Stochastic Data Streams

VIEW 13 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Private Learning Implies Online Learning: An Efficient Reduction

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Logistic Regression: The Importance of Being Improper

VIEW 7 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Multiclass Boosting with Bandit Feedback

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Online Multiclass Boosting with Bandit Feedback

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Generative Multi-Adversarial Networks

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Online Multiclass Boosting

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Drifting games

Rocco A Servedio
  • Machine Learning Boosting : Foundations and Algorithms
  • 2012

Online learning and online convex optimization

Shalev-Shwartz, Shai
  • Foundations and Trends in Machine Learning,
  • 2011

Highprobability regret bounds for bandit online linear optimization

Bartlett, L Peter, +9 authors Ambuj
  • In Proceedings of the 21st Annual Conference on Learning Theory (COLT
  • 2008
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…