English

Noise in Classification

Machine Learning 2020-11-16 v2 Data Structures and Algorithms Machine Learning

Abstract

This chapter considers the computational and statistical aspects of learning linear thresholds in presence of noise. When there is no noise, several algorithms exist that efficiently learn near-optimal linear thresholds using a small amount of data. However, even a small amount of adversarial noise makes this problem notoriously hard in the worst-case. We discuss approaches for dealing with these negative results by exploiting natural assumptions on the data-generating process.

Keywords

Cite

@article{arxiv.2010.05080,
  title  = {Noise in Classification},
  author = {Maria-Florina Balcan and Nika Haghtalab},
  journal= {arXiv preprint arXiv:2010.05080},
  year   = {2020}
}

Comments

Chapter 16 of the book Beyond the Worst-Case Analysis of Algorithms