English

Machine Learning in the String Landscape

High Energy Physics - Theory 2017-10-25 v1 High Energy Physics - Phenomenology

Abstract

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 43×2.96×10755\frac43 \times 2.96 \times 10^{755} F-theory compactifications. Logistic regression generates a new conjecture for when E6E_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.

Keywords

Cite

@article{arxiv.1707.00655,
  title  = {Machine Learning in the String Landscape},
  author = {Jonathan Carifio and James Halverson and Dmitri Krioukov and Brent D. Nelson},
  journal= {arXiv preprint arXiv:1707.00655},
  year   = {2017}
}

Comments

35 pages, 4 figures