IMSRG-Net: A machine learning-based solver for In-Medium Similarity Renormalization Group

Abstract

We present a novel method, IMSRG-Net, which utilizes machine learning techniques as a solver for the in-medium Similarity Renormalization Group (IMSRG). The primary objective of IMSRG-Net is to approximate the Magnus operators $\Omega (s)$ in the IMSRG flow equation, thereby offering an alternative to the computationally intensive part of IMSRG calculations. The key idea of IMSRG-Net is its design of the loss function inspired by physics-informed neural networks to encode the underlying {\it physics}, i.e., IMSRG flow equation, into the model. Through training on a dataset comprising ten data points with flow parameters up to $s=20$, capturing approximately one-eighth to one-quarter of the entire flow, IMSRG-Net exhibits remarkable accuracy in extrapolating the ground state energies and charge radii of ${}^{16}$O and ${}^{40}$Ca. Furthermore, this model demonstrates effectiveness in deriving effective interactions for a valence space.

arXiv comment8 pages, accepted version for Phys. Rev. C

References in corpus (29)

• Accurate Charge-Dependent Nucleon-Nucleon Potential at Fourth Order of Chiral Perturbation Theory
• The In-Medium Similarity Renormalization Group: A Novel Ab Initio Method for Nuclei
• High-quality two-nucleon potentials up to fifth order of the chiral expansion
• A Guided Tour of Ab Initio Nuclear Many-Body Theory
• Ab initio predictions link the neutron skin of ${}^{208}$Pb to nuclear forces
• In-Medium Similarity Renormalization Group for Nuclei
• Machine Learning in Nuclear Physics
• Non-Empirical Interactions for the Nuclear Shell Model: An Update
• Peripheral nucleon-nucleon scattering at fifth order of chiral perturbation theory
• In-Medium Similarity Renormalization Group for Open-Shell Nuclei
• The Magnus expansion and the in-medium similarity renormalization group
• Eigenvector continuation with subspace learning
• Converged ab initio calculations of heavy nuclei
• Eigenvector Continuation as an Efficient and Accurate Emulator for Uncertainty Quantification
• Rigorous constraints on three-nucleon forces in chiral effective field theory from fast and accurate calculations of few-body observables
• In-medium similarity renormalization group with three-body operators
• Nuclear and neutron matter $G$-matrix calculations with Ch-EFT potential including effects of three-nucleon interaction
• Efficient emulators for scattering using eigenvector continuation
• Improved many-body expansions from eigenvector continuation
• Model reduction methods for nuclear emulators
• Fast & accurate emulation of two-body scattering observables without wave functions
• Convergence of Eigenvector Continuation
• Generalizing the calculable $R$-matrix theory and eigenvector continuation to the incoming wave boundary condition
• Bogoliubov many-body perturbation theory under constraint
• Self-learning Emulators and Eigenvector Continuation
• Deep Learning the Functional Renormalization Group
• Eigenvector continuation for emulating and extrapolating two-body resonances
• Excited states from eigenvector continuation: the anharmonic oscillator
• Constructing approximate shell-model wavefunctions by eigenvector continuation

Cited by in corpus (1)

• Global Framework for Emulation of Nuclear Calculations