Machine learning Post-Minkowskian integrals
- Ryusuke Jinno(,)
- Madrid, IFT and
- DESY
- ,
- ,
26 pages
Published in:
- JHEP 07 (2023) 181
- Published: Jul 24, 2023
e-Print:
- 2209.01091 [hep-th]
Report number:
- IFT-UAM/CSIC-22-97,
- DESY-22-144,
- TUM-HEP 1392/22
View in:
Citations per year
Abstract: (Springer)
We study a neural network framework for the numerical evaluation of Feynman loop integrals that are fundamental building blocks for perturbative computations of physical observables in gauge and gravity theories. We show that such a machine learning approach improves the convergence of the Monte Carlo algorithm for high-precision evaluation of multi-dimensional integrals compared to traditional algorithms. In particular, we use a neural network to improve the importance sampling. For a set of representative integrals appearing in the computation of the conservative dynamics for a compact binary system in General Relativity, we perform a quantitative comparison between the Monte Carlo integrators VEGAS and i-flow, an integrator based on neural network sampling.Note:
- 26 pages + references, 4 figures, 3 tables, added ancillary, journal version
- Scattering Amplitudes
- Classical Theories of Gravity
- Effective Field Theories
- binary: compact
- neural network
- Monte Carlo
- machine learning
- gravitation
- general relativity
- higher-dimensional
References(167)
Figures(8)
- [7]
- [8]
- [9]
- [14]