Weak Learners and Improved Rates of Convergencein

@inproceedings{Mannor2000WeakLA,
  title={Weak Learners and Improved Rates of Convergencein},
  author={Shie Mannor},
  year={2000}
}
The problem constructing weak classiiers for boosting algorithms is studied. We present an algorithm that produces a linear classiier that is guaranteed to achieve an error better than random guessing for any distribution on the data. While this weak learner is not useful for learning in general, we show that under reasonable conditions on the distribution… CONTINUE READING