Artificial Neural Network Approach to the Analytic Continuation Problem

Abstract

Inverse problems are encountered in many domains of physics, with analytic continuation of the imaginary Green's function into the real frequency domain being a particularly important example. However, the analytic continuation problem is ill defined and currently no analytic transformation for solving it is known. We present a general framework for building an artificial neural network (ANN) that solves this task with a supervised learning approach. Application of the ANN approach to quantum Monte Carlo calculations and simulated Green's function data demonstrates its high accuracy. By comparing with the commonly used maximum entropy approach, we show that our method can reach the same level of accuracy for low-noise input data, while performing significantly better when the noise strength increases. The computational cost of the proposed neural network approach is reduced by almost three orders of magnitude compared to the maximum entropy method

arXiv comment6 pages, 4 figures, supplementary material available as ancillary file

References in corpus (6)

• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Sparse modeling approach to analytical continuation of imaginary-time quantum Monte Carlo data
• Implementation of the Maximum Entropy Method for Analytic Continuation
• Using the average spectrum method to extract dynamics from quantum Monte Carlo simulations
• Analytic continuation via domain-knowledge free machine learning
• Kernel polynomial representation of imaginary-time Green's functions

Cited by in corpus (57)

• Machine learning and the physical sciences
• Electronic Density Response of Warm Dense Matter
• Progress on stochastic analytic continuation of quantum Monte Carlo data
• Exploring QCD matter in extreme conditions with Machine Learning
• Reconstructing QCD Spectral Functions with Gaussian Processes
• Spectral Reconstruction with Deep Neural Networks
• Spectral representation of lattice gluon and ghost propagators at zero temperature
• Robust analytic continuation of Green's functions via projection, pole estimation, and semidefinite relaxation
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Reconstructing spectral functions via automatic differentiation
• Machine learning-based inversion of nuclear responses
• Rethinking the ill-posedness of the spectral function reconstruction -- why is it fundamentally hard and how Artificial Neural Networks can help
• Extending the average spectrum method: Grid points sampling and density averaging
• Non-perturbative strong coupling at timelike momenta
• ACFlow: An open source toolkit for analytical continuation of quantum Monte Carlo data
• The QCD moat regime and its real-time properties
• Robust analytic continuation combining the advantages of the sparse modeling approach and Padé approximation
• Inverse problems, real-time dynamics and lattice simulations
• Bayesian inference of real-time dynamics from lattice QCD
• Learned Optimizers for Analytic Continuation
• Neural network approach to reconstructing spectral functions and complex poles of confined particles
• Noise Enhanced Neural Networks for Analytic Continuation
• Bryan's Maximum Entropy Method -- diagnosis of a flawed argument and its remedy
• DSQSS: Discrete Space Quantum Systems Solver
• Machine learning spectral functions in lattice QCD
• Renormalized Perturbation Theory for Fast Evaluation of Feynman Diagrams on the Real Frequency Axis
• Modeling the unphysical pseudomode model with physical ensembles: simulation, mitigation, and restructuring of non-Markovian quantum noise
• Deep learning Local Reduced Density Matrices for Many-body Hamiltonian Estimation
• Stochastic pole expansion method
• Estimates of the dynamic structure factor for the finite temperature electron liquid via analytic continuation of path integral Monte Carlo data
• A deep learning approach to the measurement of long-lived memory kernels from Generalised Langevin Dynamics
• Spatial mapping of disordered 2D materials: the conductance Sudoku
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Training biases in machine learning for the analytic continuation of quantum many-body Green's functions
• Maximum entropy analytic continuation of anomalous self-energies
• Connecting Tikhonov regularization to the maximum entropy method for the analytic continuation of quantum Monte Carlo data
• Neural network enhanced hybrid quantum many-body dynamical distributions
• Efficient and quantum-adaptive machine learning with fermion neural networks
• TRIQS/Nevanlinna: Implementation of the Nevanlinna Analytic Continuation method for noise-free data
• Dual formulation of the maximum entropy method applied to analytic continuation of quantum Monte Carlo data
• Källén-Lehmann Spectral Representation of the Scalar SU(2) Glueball
• Barycentric rational function approximation made simple: A fast analytic continuation method for Matsubara Green's functions
• Rapidly Encoding Generalizable Dynamics in a Euclidean Symmetric Neural Network
• Neural Network Analytic Continuation for Monte Carlo: Improvement by Statistical Errors
• Bidirectional information flow quantum state tomography
• Decoding the conductance of disordered nanostructures: a quantum inverse problem
• Learning crystal field parameters using convolutional neural networks
• Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling
• Improving the Deconvolution of Spectrum at Finite Temperature via Neural Network
• Autoencoder-based analytic continuation method for strongly correlated quantum systems
• Analytic Continuation of Noisy Data Using Adams Bashforth ResNet
• Nevanlinna Analytic Continuation for Migdal-Eliashberg Theory
• Application of radial basis functions neutral networks in spectral functions
• Dynamically polarisable force-fields for surface simulations via multi-output classification Neural Networks
• The noiseless limit and improved-prior limit of the maximum entropy method and their implications for the analytic continuation problem
• A Parameter-Free Differential Evolution Algorithm for the Analytic Continuation of Imaginary Time Correlation Functions
• PyLIT: Reformulation and implementation of the analytic continuation problem using kernel representation methods