Saved in:
Bibliographic Details
Main Authors: Fan, Yi, Jejjala, Vishnu, Lei, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01779
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912801844363264
author Fan, Yi
Jejjala, Vishnu
Lei, Yang
author_facet Fan, Yi
Jejjala, Vishnu
Lei, Yang
contents Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$θ$ function and the elliptic Gamma function. The model learns to apply algebraic identities, particularly the SL$(2,\mathbb{Z})$ and SL$(3,\mathbb{Z})$ modular transformations, to reduce heavily scrambled expressions to their canonical forms. Experimental results show that the model achieves over 99\% accuracy on in-distribution tests and maintains robust performance (exceeding 90\% accuracy) under significant extrapolation, such as with deeper scrambling depths. This demonstrates that the model has internalized the underlying algebraic rules of modular transformations rather than merely memorizing training patterns. Our work presents the first successful application of machine learning to perform symbolic simplification using modular identities, offering a new automated tool for computations with special functions in quantum field theory and the string theory.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01779
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Machine learning modularity
Fan, Yi
Jejjala, Vishnu
Lei, Yang
High Energy Physics - Theory
Machine Learning
Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$θ$ function and the elliptic Gamma function. The model learns to apply algebraic identities, particularly the SL$(2,\mathbb{Z})$ and SL$(3,\mathbb{Z})$ modular transformations, to reduce heavily scrambled expressions to their canonical forms. Experimental results show that the model achieves over 99\% accuracy on in-distribution tests and maintains robust performance (exceeding 90\% accuracy) under significant extrapolation, such as with deeper scrambling depths. This demonstrates that the model has internalized the underlying algebraic rules of modular transformations rather than merely memorizing training patterns. Our work presents the first successful application of machine learning to perform symbolic simplification using modular identities, offering a new automated tool for computations with special functions in quantum field theory and the string theory.
title Machine learning modularity
topic High Energy Physics - Theory
Machine Learning
url https://arxiv.org/abs/2601.01779