Saved in:
Bibliographic Details
Main Authors: Rodatz, Benjamin, Fan, Ian, Laakkonen, Tuomas, Ortega, Neil John, Hoffmann, Thomas, Wang-Mascianica, Vincent
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.02424
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916718565130240
author Rodatz, Benjamin
Fan, Ian
Laakkonen, Tuomas
Ortega, Neil John
Hoffmann, Thomas
Wang-Mascianica, Vincent
author_facet Rodatz, Benjamin
Fan, Ian
Laakkonen, Tuomas
Ortega, Neil John
Hoffmann, Thomas
Wang-Mascianica, Vincent
contents We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our theoretical framework, we exhibit and implement a novel "manipulator" task that minimally edits input data to have a desired attribute. Our model-agnostic approach achieves this end-to-end, and without the need for custom architectures, adversarial training, random sampling, or interventions on the data, hence enabling capable, small-scale, and training-stable models.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02424
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Pattern Language for Machine Learning Tasks
Rodatz, Benjamin
Fan, Ian
Laakkonen, Tuomas
Ortega, Neil John
Hoffmann, Thomas
Wang-Mascianica, Vincent
Machine Learning
Category Theory
18M30, 68T01
I.2.6
We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our theoretical framework, we exhibit and implement a novel "manipulator" task that minimally edits input data to have a desired attribute. Our model-agnostic approach achieves this end-to-end, and without the need for custom architectures, adversarial training, random sampling, or interventions on the data, hence enabling capable, small-scale, and training-stable models.
title A Pattern Language for Machine Learning Tasks
topic Machine Learning
Category Theory
18M30, 68T01
I.2.6
url https://arxiv.org/abs/2407.02424