2017/07/03 by Jonathan Carifio, James Halverson, Dmitri Krioukov +1 · 113 citations
Mathematics · Physics and Astronomy · #Black Holes and Theoretical Physics #Conjecture #Decision tree #Ensemble learning #Gauge (firearms) #Geometric and Algebraic Topology #Homotopy and Cohomology in Algebraic Topology #Random forest #Rank (graph theory) #String (physics) #Tree (set theory) #hep-ph #hep-th
paper · pdf · doi:10.1007/jhep09(2017)157
published in Journal of High Energy Physics 2017(9) (Springer Nature) · 35 pages, 4 figures
arxiv created 2017/07/03 · openalex created_date 2017/07/14 · openalex publication_date 2017/09/01 · arxiv updated 2017/10/25 · openalex updated_date 2026/08/06
We utilize machine learning to study the string landscape. Deep data dives and conjecture generation are proposed as useful frameworks for utilizing machine learning in the landscape, and examples of each are presented. A decision tree accurately predicts the number of weak Fano toric threefolds arising from reflexive polytopes, each of which determines a smooth F-theory compactification, and linear regression generates a previously proven conjecture for the gauge group rank in an ensemble of (4)/(3)× 2.96× 10755 F-theory compactifications. Logistic regression generates a new conjecture for when E 6 arises in the large ensemble of F-theory compactifications, which is then rigorously proven. This result may be relevant for the appearance of visible sectors in the ensemble. Through conjecture generation, machine learning is useful not only for numerics, but also for rigorous results.