Category Theory in Machine Learning
It provides a survey for researchers interested in unifying mathematical frameworks in machine learning, but is incremental as it reviews existing applications.
The paper documents the motivations, goals, and common themes in applying category theory to machine learning, covering areas such as gradient-based learning, probability, and equivariant learning, but does not present new results or concrete numbers.
Over the past two decades machine learning has permeated almost every realm of technology. At the same time, many researchers have begun using category theory as a unifying language, facilitating communication between different scientific disciplines. It is therefore unsurprising that there is a burgeoning interest in applying category theory to machine learning. We aim to document the motivations, goals and common themes across these applications. We touch on gradient-based learning, probability, and equivariant learning.