Statistical Predictions in String Theory and Deep Generative Models

Abstract

Generative models in deep learning allow for sampling probability distributions that approximate data distributions. We propose using generative models for making approximate statistical predictions in the string theory landscape. For vacua admitting a Lagrangian description this can be thought of as learning random tensor approximations of couplings. As a concrete proof-of-principle, we demonstrate in a large ensemble of Calabi-Yau manifolds that Kahler metrics evaluated at points in Kahler moduli space are well-approximated by ensembles of matrices produced by a deep convolutional Wasserstein GAN. Accurate approximations of the Kahler metric eigenspectra are achieved with far fewer than $h^{11}$ Gaussian draws. Accurate extrapolation to values of $h^{11}$ outside the training set are achieved via a conditional GAN. Together, these results implicitly suggest the existence of strong correlations in the data, as might be expected if Reid's fantasy is correct.

arXiv comment14 pages, 4 figures

References in corpus (38)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Quantization of Four-form Fluxes and Dynamical Neutralization of the Cosmological Constant
• The statistics of string/M theory vacua
• Distributions of flux vacua
• Distributions of nonsupersymmetric flux vacua
• Probabilities in the inflationary multiverse
• Computational complexity of the landscape I
• Machine Learning in the String Landscape
• Making predictions in the multiverse
• The Wasteland of Random Supergravities
• A paradox in the global description of the multiverse
• Evolving neural networks with genetic algorithms to study the String Landscape
• Machine Learning CICY Threefolds
• Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
• Are GANs Created Equal? A Large-Scale Study
• Machine Learning Line Bundle Cohomologies of Hypersurfaces in Toric Varieties
• Scanning the skeleton of the 4D F-theory landscape
• Searching the Landscape of Flux Vacua with Genetic Algorithms
• Deep learning in the heterotic orbifold landscape
• Deep Learning the Hyperbolic Volume of a Knot
• A Global View on The Search for de-Sitter Vacua in (type IIA) String Theory
• Heavy Tails in Calabi-Yau Moduli Spaces
• Getting CICY High
• Vacuum Selection from Cosmology on Networks of String Geometries
• Moduli Stars
• On Gaussian Random Supergravity
• Distinguishing Elliptic Fibrations with AI
• Supersymmetric Vacua in Random Supergravity
• Computational complexity of the landscape II - Cosmological considerations
• Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
• On the computation of non-perturbative effective potentials in the string theory landscape -- IIB/F-theory perspective
• Formulae for Line Bundle Cohomology on Calabi-Yau Threefolds
• Search Optimization, Funnel Topography, and Dynamical Criticality on the String Landscape
• Learning non-Higgsable gauge groups in 4D F-theory
• Artificial Neural Network in Cosmic Landscape
• The Scale of Inflation in the Landscape
• Inflation with a graceful exit in a random landscape
• Learning to Inflate

Cited by in corpus (10)

• Deep learning black hole metrics from shear viscosity
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Machine Learning Lie Structures & Applications to Physics
• Hilbert Series, Machine Learning, and Applications to Physics
• The landscape of promising non-supersymmetric string models
• Disentangling a Deep Learned Volume Formula
• Predicting the orbifold origin of the MSSM
• Eigenvalues and eigenforms on Calabi-Yau threefolds
• Metastable vacua from torsion and machine learning
• Generative AI for Brane Configurations and Coamoeba