English

Model Theory and Machine Learning

Logic 2019-10-30 v1

Abstract

About 25 years ago, it came to light that a single combinatorial property determines both an important dividing line in model theory (NIP) and machine learning (PAC-learnability). The following years saw a fruitful exchange of ideas between PAC learning and the model theory of NIP structures. In this article, we point out a new and similar connection between model theory and machine learning, this time developing a correspondence between \emph{stability} and learnability in various settings of \emph{online learning.} In particular, this gives many new examples of mathematically interesting classes which are learnable in the online setting.

Keywords

Cite

@article{arxiv.1801.06566,
  title  = {Model Theory and Machine Learning},
  author = {Hunter Chase and James Freitag},
  journal= {arXiv preprint arXiv:1801.06566},
  year   = {2019}
}

Comments

13 pages