Learning Is a Kan Extension

Authors: Matthew Pugh, Nick Harris, Corina Cirstea, Jo Grundy

TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper closes the gap by proving that all error minimisation algorithms may be presented as a Kan extension. This result provides a foundation for future work to investigate the optimisation of machine learning algorithms through their presentation as Kan extensions.
Researcher Affiliation Academia Matthew Pugh EMAIL School of Electronics and Computer Science University of Southampton University Road, SO17 1BJ Jo Grundy EMAIL School of Electronics and Computer Science University of Southampton University Road, SO17 1BJ Corina Cirstea EMAIL School of Electronics and Computer Science University of Southampton University Road, SO17 1BJ Nick Harris EMAIL School of Electronics and Computer Science University of Southampton University Road, SO17 1BJ
Pseudocode No The paper describes steps and concepts using mathematical definitions, theorems, and proofs, but does not present any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets No This paper is theoretical and does not conduct experiments that utilize datasets. While previous work is cited that used the 'Occupancy Dataset', this paper itself does not use or provide access information for any dataset.
Dataset Splits No This paper is theoretical and does not describe any experimental setups involving dataset splits.
Hardware Specification No This paper is theoretical and does not describe any experimental procedures that would require hardware specifications.
Software Dependencies No This paper is theoretical and does not describe any experimental procedures that would require specific software dependencies with version numbers.
Experiment Setup No This paper is theoretical and does not conduct experiments, therefore, it does not provide details on experimental setup or hyperparameters.