A General Method for Robust Learning from Batches
Machine Learning
2020-02-26 v1 Information Theory
Machine Learning
math.IT
Statistics Theory
Statistics Theory
Abstract
In many applications, data is collected in batches, some of which are corrupt or even adversarial. Recent work derived optimal robust algorithms for estimating discrete distributions in this setting. We consider a general framework of robust learning from batches, and determine the limits of both classification and distribution estimation over arbitrary, including continuous, domains. Building on these results, we derive the first robust agnostic computationally-efficient learning algorithms for piecewise-interval classification, and for piecewise-polynomial, monotone, log-concave, and gaussian-mixture distribution estimation.
Cite
@article{arxiv.2002.11099,
title = {A General Method for Robust Learning from Batches},
author = {Ayush Jain and Alon Orlitsky},
journal= {arXiv preprint arXiv:2002.11099},
year = {2020}
}
Comments
First Draft