arXiv:1801.06566 Abstract | arXiv Analytics

arXiv:1801.06566 [math.LO]Abstract References Reviews Resources

Model Theory and Machine Learning

Published 2018-01-19Version 1

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.

Comments: 13 pages

Categories: math.LO

Subjects: 03C95, 03C98, 03C45

Keywords: model theory, machine learning, single combinatorial property determines, similar connection, nip structures

Related articles: Most relevant | Search more

arXiv:math/0702468 [math.LO] (Published 2007-02-15)

Model theory and Kaehler geometry

Rahim Moosa, Anand Pillay

arXiv:1801.07640 [math.LO] (Published 2018-01-23)

Model theory and combinatorics of banned sequences

Hunter Chase, James Freitag

arXiv:1705.00159 [math.LO] (Published 2017-04-29)