A New Perspective on Learning Linear Separators with Large \(L_qL_p\) Margins

@inproceedings{Balcan2014ANP,
  title={A New Perspective on Learning Linear Separators with Large \(L_qL_p\) Margins},
  author={Maria-Florina Balcan and Christopher Berlind},
  booktitle={AISTATS},
  year={2014}
}
We give theoretical and empirical results that provide new insights into large margin learning. We prove a bound on the generalization error of learning linear separators with large LqLp margins (where Lq and Lp are dual norms) for any finite p ≥ 1. The bound leads to a simple data-dependent sufficient condition for fast learning in addition to extending… CONTINUE READING