Category-Theoretical and Topos-Theoretical Frameworks in Machine Learning: A Survey
Open Access
Abstract
In this survey, we provide an overview of category theory-derived machine learning from four mainstream perspectives: gradient-based learning, probability-based learning, invariance and equivalence-based learning, and topos-based learning. For the first three topics, we primarily review research in the past five years, updating and expanding on the previous survey by Shiebler et al. The fourth topic, which delves into higher category theory, particularly topos theory, is surveyed for the first time in this paper. In certain machine learning methods, the compositionality of functors plays a vital role, prompting the development of specific categorical frameworks. However, when considering how the global properties of a network reflect in local structures and how geometric properties and semantics are expressed with logic, the topos structure becomes particularly significant and profound.Keywords
All Related Versions
Funding Information
- Japan Society for the Promotion of Science (JP22K13951, YBZ202206)
- Doctoral Science Foundation of Xichang University (JP22K13951, YBZ202206)
This publication has 53 references indexed in Scilit:
- Computing with Categories in Machine Learning2023
- A Framework for Differential Calculus on Persistence BarcodesFoundations of Computational Mathematics, 2021
- A Topos-Based Approach to Building Language OntologiesLecture Notes in Computer Science, 2019
- Relational Reasoning for Markov Chains in a Probabilistic Guarded Lambda Calculus2018
- Random Measures, Theory and Applications2017
- Classifying Clustering SchemesFoundations of Computational Mathematics, 2013
- Optimal Transport2009
- Foundations of Modern Probability2002
- A categorical approach to probability theory1982
- Categorical Aspects of Topology and Analysis1982