AI advances in theoretical high-energy physics

ORAL  · Invited

Abstract

AI is now being widely employed for tasks previously considered the domain of theoretical physicists. This talk will explore recent successes of AI in key areas such as identifying symmetries, building BSM models, performing symbolic regression, and discovering new data structures and representations. Beyond current AI, the talk will also touch on the future: the rise of quantum computing will establish quantum machine learning as a powerful tool for modeling, optimization, and data analysis. Crucially, the advent of Large Language Models (LLMs) allows for sophisticated agentic AI to optimize simulation pipelines in particle phenomenology and serve as a true collaborator to human theorists.

–

Publication: K. T. Matchev, A. Roman and P. Shyamsundar, ``Uncertainties associated with GAN-generated datasets in high energy physics,''
SciPost Phys. 12, no.3, 104 (2022) doi:10.21468/SciPostPhys.12.3.104 [arXiv:2002.06307 [hep-ph]].

D. Kim, K. Kong, K. T. Matchev, M. Park and P. Shyamsundar, ``Deep-learned event variables for collider phenomenology,''
Phys. Rev. D 107, no.3, L031904 (2023) doi:10.1103/PhysRevD.107.L031904 [arXiv:2105.10126 [hep-ph]].

Z. Dong, K. Kong, K. T. Matchev and K. Matcheva, ``Is the machine smarter than the theorist: Deriving formulas for particle kinematics with symbolic regression,'' Phys. Rev. D 107, no.5, 055018 (2023) doi:10.1103/PhysRevD.107.055018 [arXiv:2211.08420 [hep-ph]].

R. T. Forestano, K. T. Matchev, K. Matcheva, A. Roman, E. B. Unlu and S. Verner, ``Deep learning symmetries and their Lie groups, algebras, and subalgebras from first principles,'' Mach. Learn. Sci. Tech. 4, no.2, 025027 (2023) doi:10.1088/2632-2153/acd989 [arXiv:2301.05638 [hep-ph]].

A. Roman, R. T. Forestano, K. T. Matchev, K. Matcheva and E. B. Unlu, ``Oracle-Preserving Latent Flows,'' [arXiv:2302.00806 [cs.LG]].

R. T. Forestano, K. T. Matchev, K. Matcheva, A. Roman, E. B. Unlu and S. Verner, ``Discovering sparse representations of Lie groups with machine learning,'' Phys. Lett. B 844, 138086 (2023) doi:10.1016/j.physletb.2023.138086 [arXiv:2302.05383 [hep-ph]].

R. T. Forestano, K. T. Matchev, K. Matcheva, A. Roman, E. B. Unlu and S. Verner, ``Accelerated discovery of machine-learned symmetries: Deriving the exceptional Lie groups G2, F4 and E6,'' Phys. Lett. B 847, 138266 (2023) doi:10.1016/j.physletb.2023.138266 [arXiv:2307.04891 [hep-th]].

R. T. Forestano, K. T. Matchev, K. Matcheva, A. Roman, E. B. Unlu and S. Verner, ``Identifying the group-theoretic structure of machine-learned symmetries,'' Phys. Lett. B 847, 138306 (2023) doi:10.1016/j.physletb.2023.138306 [arXiv:2309.07860 [hep-ph]].

K. T. Matchev, K. Matcheva, P. Ramond and S. Verner, ``Exploring the truth and beauty of theory landscapes with machine learning,''
Phys. Lett. B \textbf{856}, 138941 (2024) doi:10.1016/j.physletb.2024.138941 [arXiv:2401.11513 [hep-ph]].

Presenters

  • Konstantin T Matchev

    • University of Florida
    • University of Alabama

Authors

  • Konstantin T Matchev

    • University of Florida
    • University of Alabama