Learning first-order definable concepts over structures of small degree
Machine Learning
2017-01-20 v1 Logic in Computer Science
Abstract
We consider a declarative framework for machine learning where concepts and hypotheses are defined by formulas of a logic over some background structure. We show that within this framework, concepts defined by first-order formulas over a background structure of at most polylogarithmic degree can be learned in polylogarithmic time in the "probably approximately correct" learning sense.
Cite
@article{arxiv.1701.05487,
title = {Learning first-order definable concepts over structures of small degree},
author = {Martin Grohe and Martin Ritzert},
journal= {arXiv preprint arXiv:1701.05487},
year = {2017}
}