An autoencoder for heterotic orbifolds with arbitrary geometry

TL;DR

This paper introduces a deep autoencoder designed to efficiently encode and analyze the complex parameter spaces of heterotic orbifold models, potentially simplifying their classification.

Contribution

We developed a general deep autoencoder for heterotic orbifold models that can encode large parameter spaces across various geometries with high accuracy.

Findings

Autoencoder successfully compresses large parameter spaces.

Models with desirable features cluster in bounded regions.

Method applicable to multiple orbifold geometries.

Abstract

Artificial neural networks have become important to improve the search for admissible string compactifications and characterize them. In this paper we construct the heterotic orbiencoder, a general deep autoencoder to study heterotic orbifold models arising from various Abelian orbifold geometries. Our neural network can be easily trained to successfully encode the large parameter space of many orbifold geometries simultaneously, independently of the statistical dissimilarities of their training features. In particular, we show that our autoencoder is capable of compressing with good accuracy the large parameter space of two promising orbifold geometries in just three parameters. Further, most orbifold models with phenomenologically appealing features appear in bounded regions of this small space. Our contribution hints towards a possible simplification of the classification of (promising) heterotic orbifold models.