Efficient Co-Training of Linear Separators Under Weak Dependence

Abstract

We develop the first polynomial-time algorithm for co-training of homogeneous linear separators under \em weak dependence, a relaxation of the condition of independence given the label. Our algorithm learns from purely unlabeled data, except for a single labeled example to break symmetry of the two classes, and works for any data distribution having an inverse-polynomial margin and with center of mass at the origin.

Cite

Text

Blum and Mansour. "Efficient Co-Training of Linear Separators Under Weak Dependence." Proceedings of the 2017 Conference on Learning Theory, 2017.

Markdown

[Blum and Mansour. "Efficient Co-Training of Linear Separators Under Weak Dependence." Proceedings of the 2017 Conference on Learning Theory, 2017.](https://mlanthology.org/colt/2017/blum2017colt-efficient/)

BibTeX

@inproceedings{blum2017colt-efficient,
  title     = {{Efficient Co-Training of Linear Separators Under Weak Dependence}},
  author    = {Blum, Avrim and Mansour, Yishay},
  booktitle = {Proceedings of the 2017 Conference on Learning Theory},
  year      = {2017},
  pages     = {302-318},
  volume    = {65},
  url       = {https://mlanthology.org/colt/2017/blum2017colt-efficient/}
}