NeurIPS 2020poster26 citations
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.
BibTeX
@inproceedings{NEURIPS2020_f7a82ce7,
author = {Jain, Ayush and Orlitsky, Alon},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {21775--21785},
publisher = {Curran Associates, Inc.},
title = {A General Method for Robust Learning from Batches},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/f7a82ce7e16d9687e7cd9a9feb85d187-Paper.pdf},
volume = {33},
year = {2020}
}