Saved in:
Bibliographic Details
Main Authors: Jejjala, Vishnu, Nampuri, Suresh, Nxumalo, Dumisani, Roy, Pratik, Swain, Abinash
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.05549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909605781569536
author Jejjala, Vishnu
Nampuri, Suresh
Nxumalo, Dumisani
Roy, Pratik
Swain, Abinash
author_facet Jejjala, Vishnu
Nampuri, Suresh
Nxumalo, Dumisani
Roy, Pratik
Swain, Abinash
contents Modular, Jacobi, and mock-modular forms serve as generating functions for BPS black hole degeneracies. By training feed-forward neural networks on Fourier coefficients of automorphic forms derived from the Dedekind eta function, Eisenstein series, and Jacobi theta functions, we demonstrate that machine learning techniques can accurately predict modular weights from truncated expansions. Our results reveal strong performance for negative weight modular and quasi-modular forms, particularly those arising in exact black hole counting formulae, with lower accuracy for positive weights and more complicated combinations of Jacobi theta functions. This study establishes a proof of concept for using machine learning to identify how data is organized in terms of modular symmetries in gravitational systems and suggests a pathway toward automated detection and verification of symmetries in quantum gravity.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine learning automorphic forms for black holes
Jejjala, Vishnu
Nampuri, Suresh
Nxumalo, Dumisani
Roy, Pratik
Swain, Abinash
High Energy Physics - Theory
Machine Learning
Number Theory
Modular, Jacobi, and mock-modular forms serve as generating functions for BPS black hole degeneracies. By training feed-forward neural networks on Fourier coefficients of automorphic forms derived from the Dedekind eta function, Eisenstein series, and Jacobi theta functions, we demonstrate that machine learning techniques can accurately predict modular weights from truncated expansions. Our results reveal strong performance for negative weight modular and quasi-modular forms, particularly those arising in exact black hole counting formulae, with lower accuracy for positive weights and more complicated combinations of Jacobi theta functions. This study establishes a proof of concept for using machine learning to identify how data is organized in terms of modular symmetries in gravitational systems and suggests a pathway toward automated detection and verification of symmetries in quantum gravity.
title Machine learning automorphic forms for black holes
topic High Energy Physics - Theory
Machine Learning
Number Theory
url https://arxiv.org/abs/2505.05549