A General Method for Robust Learning from Batches

Abstract

In many applications, data is collected in batches, some of which may be corrupt or even adversarial. Recent work derived optimal robust algorithms for estimating finite distributions in this setting. We develop a general framework of robust learning from batches, and determine the limits of both distribution estimation, and notably, classification, over arbitrary, including continuous, domains.

PDF NeurIPS Semantic Scholar

Cite

Text

Jain and Orlitsky. "A General Method for Robust Learning from Batches." Neural Information Processing Systems, 2020.

Markdown

[Jain and Orlitsky. "A General Method for Robust Learning from Batches." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/jain2020neurips-general/)

BibTeX

@inproceedings{jain2020neurips-general,
  title     = {{A General Method for Robust Learning from Batches}},
  author    = {Jain, Ayush and Orlitsky, Alon},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/jain2020neurips-general/}
}