Learning BPS Spectra and the Gap Conjecture
arXiv:2405.09993 · doi:10.1103/PhysRevD.110.046016
Abstract
We explore statistical properties of BPS q-series for 3d N=2 strongly coupled supersymmetric theories that correspond to a particular family of 3-manifolds Y. We discover that gaps between exponents in the q-series are statistically more significant at the beginning of the q-series compared to gaps that appear in higher powers of q. Our observations are obtained by calculating saliencies of q-series features used as input data for principal component analysis, which is a standard example of an explainable machine learning technique that allows for a direct calculation and a better analysis of feature saliencies.
arXiv comment11 pages, 4 figures, 3 tables
References in corpus (16)
- Microscopic Origin of the Bekenstein-Hawking Entropy
- On the Geometry of the String Landscape and the Swampland
- Fivebranes and 3-manifold homology
- Walls, Lines, and Spectral Dualities in 3d Gauge Theories
- Machine Learning of Calabi-Yau Volumes
- Machine Learning in the String Landscape
- Deep Learning and AdS/CFT
- Evolving neural networks with genetic algorithms to study the String Landscape
- 3d Modularity
- Deep Learning the Hyperbolic Volume of a Knot
- Machine Learning Line Bundle Cohomology
- Higher depth quantum modular forms and plumbed -manifolds
- Hilbert Series, Machine Learning, and Applications to Physics
- Unsupervised Machine Learning Techniques for Exploring Tropical Coamoeba, Brane Tilings and Seiberg Duality
- Machine Learning Regularization for the Minimum Volume Formula of Toric Calabi-Yau 3-folds
- Machine learning the dimension of a Fano variety