Neural Network Analytic Continuation for Monte Carlo: Improvement by Statistical Errors
arXiv:2302.11317 · doi:10.1088/1674-1056/accd4c
Abstract
This study explores the use of neural network-based analytic continuation to extract spectra from Monte Carlo data. We apply this technique to both synthetic and Monte Carlo-generated data. The training sets for neural networks are carefully synthesized without ``data leakage". We found that the training set should match the input correlation functions in terms of statistical error properties, such as noise level, noise dependence on imaginary time, and imaginary time-displaced correlations. We have developed a systematic method to synthesize such training datasets. Our improved algorithm outperform the widely used maximum entropy method in highly noisy situations. As an example, our method successfully extracted the dynamic structure factor of the spin-1/2 Heisenberg chain from quantum Monte Carlo simulations.
References in corpus (13)
- Deep Learning using Rectified Linear Units (ReLU)
- Stochastic series expansion method with operator-loop update
- Sensitivity and Generalization in Neural Networks: an Empirical Study
- Algorithms for optimized maximum entropy and diagnostic tools for analytic continuation
- Constrained sampling method for analytic continuation
- Maximum entropy formalism for the analytic continuation of matrix-valued Green's functions
- Artificial Neural Network Approach to the Analytic Continuation Problem
- Progress on stochastic analytic continuation of quantum Monte Carlo data
- Analytic continuation via domain-knowledge free machine learning
- Monte Carlo study of a two-dimensional quantum ferromagnet
- Accuracy of the microcanonical Lanczos method to compute real-frequency dynamical spectral functions of quantum models at finite temperatures
- Noise Enhanced Neural Networks for Analytic Continuation
- Training biases in machine learning for the analytic continuation of quantum many-body Green's functions