English

General supervised learning as change propagation with delta lenses

Logic in Computer Science 2021-07-12 v4 Category Theory

Abstract

Delta lenses are an established mathematical framework for modelling and designing bidirectional model transformations. Following the recent observations by Fong et al, the paper extends the delta lens framework with a a new ingredient: learning over a parameterized space of model transformations seen as functors. We define a notion of an asymmetric learning delta lens with amendment (ala-lens), and show how ala-lenses can be organized into a symmetric monoidal (sm) category. We also show that sequential and parallel composition of well-behaved ala-lenses are also well-behaved so that well-behaved ala-lenses constitute a full sm-subcategory of ala-lenses.

Keywords

Cite

@article{arxiv.1911.12904,
  title  = {General supervised learning as change propagation with delta lenses},
  author = {Zinovy Diskin},
  journal= {arXiv preprint arXiv:1911.12904},
  year   = {2021}
}

Comments

An extended version of paper with the same title published at FOSSACS 2020. Unfortunately, both the paper and the previous version of the extended version uploaded to arxiv on Feb 26, 2020, had bad typos in Definition 4 and Fig.4, which are now fixed

R2 v1 2026-06-23T12:30:34.172Z