Journal
BULLETIN OF SYMBOLIC LOGIC
Volume 25, Issue 3, Pages 319-332Publisher
CAMBRIDGE UNIV PRESS
DOI: 10.1017/bsl.2018.71
Keywords
model theory; machine learning
Categories
Funding
- NSF [1700095]
- Direct For Mathematical & Physical Scien
- Division Of Mathematical Sciences [1700095] Funding Source: National Science Foundation
Ask authors/readers for more resources
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 stability and learnability in various settings of online learning. In particular, this gives many new examples of mathematically interesting classes which are learnable in the online setting.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available