Transformers to Predict the Applicability of Symbolic Integration Routines

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barket, Rashid, Shafiq, Uzma, England, Matthew, Gerhard, Juergen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909373771546624
author Barket, Rashid
Shafiq, Uzma
England, Matthew
Gerhard, Juergen
author_facet Barket, Rashid
Shafiq, Uzma
England, Matthew
Gerhard, Juergen
contents Symbolic integration is a fundamental problem in mathematics: we consider how machine learning may be used to optimise this task in a Computer Algebra System (CAS). We train transformers that predict whether a particular integration method will be successful, and compare against the existing human-made heuristics (called guards) that perform this task in a leading CAS. We find the transformer can outperform these guards, gaining up to 30% accuracy and 70% precision. We further show that the inference time of the transformer is inconsequential which shows that it is well-suited to include as a guard in a CAS. Furthermore, we use Layer Integrated Gradients to interpret the decisions that the transformer is making. If guided by a subject-matter expert, the technique can explain some of the predictions based on the input tokens, which can lead to further optimisations.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23948
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transformers to Predict the Applicability of Symbolic Integration Routines
Barket, Rashid
Shafiq, Uzma
England, Matthew
Gerhard, Juergen
Machine Learning
Symbolic Computation
Symbolic integration is a fundamental problem in mathematics: we consider how machine learning may be used to optimise this task in a Computer Algebra System (CAS). We train transformers that predict whether a particular integration method will be successful, and compare against the existing human-made heuristics (called guards) that perform this task in a leading CAS. We find the transformer can outperform these guards, gaining up to 30% accuracy and 70% precision. We further show that the inference time of the transformer is inconsequential which shows that it is well-suited to include as a guard in a CAS. Furthermore, we use Layer Integrated Gradients to interpret the decisions that the transformer is making. If guided by a subject-matter expert, the technique can explain some of the predictions based on the input tokens, which can lead to further optimisations.
title Transformers to Predict the Applicability of Symbolic Integration Routines
topic Machine Learning
Symbolic Computation
url https://arxiv.org/abs/2410.23948