Testing Swampland Conjectures with Machine Learning

Abstract

We consider Type IIB compactifications on an isotropic torus $T^6$ threaded by geometric and non geometric fluxes. For this particular setup we apply supervised machine learning techniques, namely an artificial neural network coupled to a genetic algorithm, in order to obtain more than sixty thousand flux configurations yielding to a scalar potential with at least one critical point. We observe that both stable AdS vacua with large moduli masses and small vacuum energy as well as unstable dS vacua with small tachyonic mass and large energy are absent, in accordance to the Refined de Sitter Conjecture. Moreover, by considering a hierarchy among fluxes, we observe that perturbative solutions with small values for the vacuum energy and moduli masses are favored, as well as scenarios in which the lightest modulus mass is much greater than the corresponding AdS vacuum scale. Finally we apply some results on Random Matrix Theory to conclude that the most probable mass spectrum derived from this string setup is that satisfying the Refined de Sitter and AdS scale conjectures.

arXiv comment30 pages, 14 Figures. (v2) References added

References in corpus (22)

• Distance and de Sitter Conjectures on the Swampland
• On the Cosmological Implications of the String Swampland
• AdS and the Swampland
• Large Deviations of Extreme Eigenvalues of Random Matrices
• Towards Universal Axion Inflation and Reheating in String Theory
• The tension between 10D supergravity and dS uplifts
• The web of swampland conjectures and the TCC bound
• A Flux-Scaling Scenario for High-Scale Moduli Stabilization in String Theory
• Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
• Bounds on Slow Roll at the Boundary of the Landscape
• A Systematic Approach to Kähler Moduli Stabilisation
• More stable dS vacua from S-dual non-geometric fluxes
• The quantum swampland
• Genetic Algorithms and the Search for Viable String Vacua
• Deep learning in the heterotic orbifold landscape
• The Flux-Scaling Scenario: De Sitter Uplift and Axion Inflation
• GANs for generating EFT models
• Distinguishing Elliptic Fibrations with AI
• Contrast data mining for the MSSM from strings
• de Sitter Minima from M theory and String theory
• Revisiting constraints on uplifts to de Sitter vacua
• Baryons from Mesons: A Machine Learning Perspective

Cited by in corpus (1)

• evortran: a modern Fortran package for genetic algorithms with applications from LHC data fitting to LISA signal reconstruction