ML Anthology

Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning?

Amit Daniely, Vitaly Feldman
COLT 2019 pp. 3180-3184
/colt/2019/daniely2019colt-open/

Abstract

We ask whether every class of Boolean functions that has polynomial margin complexity can be PAC learned efficiently by a non-interactive locally differentially private algorithm.

PDF COLT Semantic Scholar

Cite

Text

Daniely and Feldman. "Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning?." Conference on Learning Theory, 2019.

Markdown

[Daniely and Feldman. "Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning?." Conference on Learning Theory, 2019.](https://mlanthology.org/colt/2019/daniely2019colt-open/)

BibTeX

@inproceedings{daniely2019colt-open,
  title     = {{Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning?}},
  author    = {Daniely, Amit and Feldman, Vitaly},
  booktitle = {Conference on Learning Theory},
  year      = {2019},
  pages     = {3180-3184},
  volume    = {99},
  url       = {https://mlanthology.org/colt/2019/daniely2019colt-open/}
}