On the solution of Euclidean path integrals with neural networks
arXiv:2509.16953 · doi:10.1093/ptep/ptag029
Abstract
This paper proposes a numerical method using neural networks to solve the path integral problem in quantum mechanics for arbitrary potentials. The method is based on a radial basis function expansion of the interaction term that appears in the Euclidean path integral formalism. By constructing a corresponding multi-layered perceptron-type neural network with exponential nonlinearities in the hidden layer, the original path integral can be approximated by a linear combination of Gaussian path integrals that can be solved analytically. The method has been tested for the double-well potential that includes a quadratic and a quartic term, giving very good, within a few percent agreement between the true and estimated bound state wave functions that are extracted from the propagator at large Euclidean times. The proposed method can also be used to describe potentials that have imaginary parts, which is tested for a simple Gaussian path integral with complex frequencies, where the model uncertainty stays below one percent for both the real and imaginary parts of the propagator.
References in corpus (16)
- Calculation of the hadronic vacuum polarization contribution to the muon anomalous magnetic moment
- Can stochastic quantization evade the sign problem? -- the relativistic Bose gas at finite chemical potential
- Improving aircraft performance using machine learning: a review
- A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
- Finite-density lattice QCD and sign problem: current status and open problems
- Stochastic quantization at finite chemical potential
- From euclidean field theory to quantum field theory
- Autoencoder-based Anomaly Detection System for Online Data Quality Monitoring of the CMS Electromagnetic Calorimeter
- Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
- Fixed-energy inverse scattering with radial basis function neural networks and its application to neutron-alpha interactions
- Higgs-boson production in the full theory at NNLO+PS
- Lattice QCD at Finite Temperature and Density
- Conformal Fields from Neural Networks
- A New Method for the Calculation of Functional and Path Integrals
- Addressing the sign-problem in Euclidean path integrals with radial basis function neural networks
- Nonautonomous Volterra Series Expansion of the Variable Phase Approximation and its Application to the Nucleon-Nucleon Inverse Scattering Problem