Machine-learning approach to finite-size effects in systems with strongly interacting fermions

Abstract

We investigate the applicability of machine learning techniques in studying the finite-size effects associated with many-body physics. These techniques have an emerging presence in many-body theory as they have been used for interpolations, extrapolations, and in modeling wavefunctions. We will resolve several issues associated with machine learning and many-body calculations such as small datasets, outliers, and discontinuities, for the purpose of extrapolating finite calculations to macroscopic scales. We carry out a systematic investigation of two related systems by developing metrics that aim to avoid spurious effects and capture desired features. This work uses neural networks to extrapolate the Unitary Gas to the thermodynamic limit at zero-range, which is otherwise difficult to reach. The effective mass of strongly interacting neutron matter is also studied and makes use of the non-interacting problem to resolve discontinuous predictions. For this investigation, we also carried out new Auxiliary Field Diffusion Monte Carlo (AFDMC) calculations for a variety of densities and particle numbers. Ultimately, we demonstrate an effective utility for neural networks in this context.

arXiv comment10 pages, 9 figures; v2 corresponds to published version

References in corpus (58)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Theory of ultracold Fermi gases
• Chiral effective field theory and nuclear forces
• Machine learning phases of matter
• Quantum Monte Carlo calculations of nuclei with A \leq 7
• Quantum Monte Carlo methods for nuclear physics
• Revealing the Superfluid Lambda Transition in the Universal Thermodynamics of a Unitary Fermi Gas
• The maximum mass and radius of neutron stars and the nuclear symmetry energy
• Chiral three-nucleon forces and neutron matter
• Neutron matter at next-to-next-to-next-to-leading order in chiral effective field theory
• Deep Learning and its Application to LHC Physics
• The Equation of State of a Low-Temperature Fermi Gas with Tunable Interactions
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Reconstructing quantum states with generative models
• Quantum Monte Carlo Calculations with Chiral Effective Field Theory Interactions
• Self-Learning Monte Carlo Method
• Precise characterization of ^6Li Feshbach resonances using trap-sideband resolved RF spectroscopy of weakly bound molecules
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Low-density neutron matter
• Coupled-cluster calculations of nucleonic matter
• Leading chiral three-nucleon forces along isotope chains in the calcium region
• Quantum Monte Carlo calculation of the equation of state of neutron matter
• Quantum Monte Carlo Calculations of Neutron Matter
• Quantum Monte Carlo calculations of neutron matter with chiral three-body forces
• Light-nuclei spectra from chiral dynamics
• Neutron Matter from Low to High Density
• Auxiliary Field quantum Monte Carlo for Strongly Paired Fermions
• Thermodynamic Measurements in a Strongly Interacting Fermi Gas
• Finite-size correction in many-body electronic structure calculations
• Resonantly Interacting Fermions In a Box
• Correlated density-dependent chiral forces for infinite matter calculations within the Green's function approach
• Properties of nuclei up to $A=16$ using local chiral interactions
• Nuclear mass systematics using neural networks
• Quantum Monte Carlo calculations of neutron matter with non-local chiral interactions
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Taming nuclear complexity with a committee of multilayer neural networks
• Auxiliary-Field Quantum Monte Carlo Simulations of Neutron Matter in Chiral Effective Field Theory
• Neutron matter at zero temperature with auxiliary field diffusion Monte Carlo
• Comparative study of neutron and nuclear matter with simplified Argonne nucleon-nucleon potentials
• BEC-BCS crossover and universal relations in unitary Fermi gases
• Self-learning Monte Carlo with Deep Neural Networks
• Quantum Monte Carlo approaches to nuclear and atomic physics
• Effective-Range Dependence of Resonantly Interacting Fermions
• Deep learning: Extrapolation tool for ab initio nuclear theory
• Machine learning the deuteron
• Extrapolation of nuclear structure observables with artificial neural networks
• Machine learning density functional theory for the Hubbard model
• Static Response of Neutron Matter
• Ferromagnetism of a Repulsive Atomic Fermi Gas in an Optical Lattice: a Quantum Monte Carlo Study
• Machine learning-based inversion of nuclear responses
• Exact representations of many body interactions with RBM neural networks
• Non-perturbative Extraction of the Effective Mass in Neutron Matter
• From bare interactions, low--energy constants and unitary gas to nuclear density functionals without free parameters: application to neutron matter
• Linear response theory in asymmetric nuclear matter for Skyrme functionals including spin-orbit and tensor terms
• Clustering of Four-Component Unitary Fermions
• Superfluid neutron matter with a twist
• Spin Susceptibility in Neutron Matter from Quantum Monte Carlo Calculations
• Neutron matter at the interface(s): static response and effective mass

Cited by in corpus (5)

• Machine Learning in Nuclear Physics
• Multi-task learning on nuclear masses and separation energies with the kernel ridge regression
• Physically Interpretable Machine Learning for nuclear masses
• Nuclear energy density functionals from machine learning
• Neural-Network Quantum States for Periodic Systems in Continuous Space