Machine learning post-Minkowskian integrals
From MaRDI portal
Abstract: 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.
Recommendations
- Advanced Monte Carlo Methods to Neural Networks
- Grassmann integrals by machine
- Feynman integrals from positivity constraints
- CosmicNet. Part I. Physics-driven implementation of neural networks within Einstein-Boltzmann Solvers
- Exact conservation laws for neural network integrators of dynamical systems
Cites work
- A GPU compatible quasi-Monte Carlo integrator interfaced to pySecDec
- A geometric method of sector decomposition
- A new algorithm for adaptive multidimensional integration
- Adaptive multidimensional integration: \textsc{vegas} enhanced
- All things retarded: radiation-reaction in worldline quantum field theory
- Amplitudes, observables, and classical scattering
- An automatized algorithm to compute infrared divergent multi-loop integrals.
- Analytic tools for Feynman integrals
- Black hole binary dynamics from the double copy and effective theory
- Classical black hole scattering from a worldline quantum field theory
- Classical gravitational scattering at \(\mathcal{O} (G^3)\) from Feynman diagrams
- Classical gravitational scattering from a gauge-invariant double copy
- Classical gravitational self-energy from double copy
- Classical space-times from the S-matrix
- Cuba -- a library for multidimensional numerical integration
- Dynamics of binary systems to fourth post-Minkowskian order from the effective field theory approach
- Effective field theory methods to model compact binaries
- Extremal black hole scattering at \(\mathcal{O} (G^3)\): graviton dominance, eikonal exponentiation, and differential equations
- FIESTA 3: cluster-parallelizable multiloop numerical calculations in physical regions
- FIESTA4: optimized Feynman integral calculations with GPU support
- FIESTA5: numerical high-performance Feynman integral evaluation
- FIRE6: Feynman integral reduction with modular arithmetic
- Feynman integral evaluation by a sector decomposition approach (FIESTA)
- Foam: A general purpose Monte Carlo cellular algorithm
- From boundary data to bound states
- From boundary data to bound states. II: Scattering angle to dynamical invariants (with twist)
- From boundary data to bound states. III: Radiative effects
- Gravitational radiation from post-Newtonian sources and inspiralling compact binaries
- High-order post-Newtonian contributions to gravitational self-force effects in black hole spacetimes
- Hypexp 2, expanding hypergeometric functions about half-integer parameters
- Hypexp, a Mathematica package for expanding hypergeometric functions around integer-valued parameters
- Integral reduction with Kira 2.0 and finite field methods
- Leading nonlinear tidal effects and scattering amplitudes
- Observables and amplitudes for spinning particles and black holes
- On-shell heavy particle effective theories
- Parallel integer relation detection: techniques and applications
- Post-Minkowskian radial action from soft limits and velocity cuts
- Progress in effective field theory approach to the binary inspiral problem
- Proof of the Bogoliubov-Parasiuk theorem on renormalization
- Quasi-Monte Carlo integration
- Radiated momentum in the post-Minkowskian worldline approach via reverse unitarity
- Radiation reaction from soft theorems
- Radiation-reaction in the effective field theory approach to post-Minkowskian dynamics
- Resolution of singularities for multi-loop integrals
- SECTOR DECOMPOSITION
- SUSY in the sky with gravitons
- Scattering in black hole backgrounds and higher-spin amplitudes. I.
- Scattering of spinning black holes from exponentiated soft factors
- SecDec-3.0: numerical evaluation of multi-scale integrals beyond one loop
- SecDec: A general program for sector decomposition
- Second-order post-Minkowskian scattering in arbitrary dimensions
- Singularities and Discontinuities of Feynman Amplitudes
- Testing binary dynamics in gravity at the sixth post-Newtonian level
- The 6th post-Newtonian potential terms at O( G_N^4)
- The H-graph with equal masses in terms of multiple polylogarithms
- The amplitude for classical gravitational scattering at third post-Minkowskian order
- The effective field theorist's approach to gravitational dynamics
- The effective field theory and perturbative analysis for log-density fields
- The effective field theory of cosmological large scale structures
- The eikonal approach to gravitational scattering and radiation at \(\mathcal{O} (G^3)\)
- The fifth-order post-Newtonian Hamiltonian dynamics of two-body systems from an effective field theory approach
- The fifth-order post-newtonian Hamiltonian dynamics of two-body systems from an effective field theory approach: potential contributions
- The power of pyramid decomposition in Normaliz
- The regional strategy in the asymptotic expansion of two-loop vertex Feynman diagrams
- Tidal effects in quantum field theory
- \texttt{FIESTA 2}: parallelizeable multiloop numerical calculations
- pySecDec: a toolbox for the numerical evaluation of multi-scale integrals
Cited in
(4)
This page was built for publication: Machine learning post-Minkowskian integrals
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6055788)
