Analytic Continuation of Noisy Data Using Adams Bashforth ResNet
arXiv:1905.10430
Abstract
We propose a data-driven learning framework for the analytic continuation problem in numerical quantum many-body physics. Designing an accurate and efficient framework for the analytic continuation of imaginary time using computational data is a grand challenge that has hindered meaningful links with experimental data. The standard Maximum Entropy (MaxEnt)-based method is limited by the quality of the computational data and the availability of prior information. Also, the MaxEnt is not able to solve the inversion problem under high level of noise in the data. Here we introduce a novel learning model for the analytic continuation problem using a Adams-Bashforth residual neural network (AB-ResNet). The advantage of this deep learning network is that it is model independent and, therefore, does not require prior information concerning the quantity of interest given by the spectral function. More importantly, the ResNet-based model achieves higher accuracy than MaxEnt for data with higher level of noise. Finally, numerical examples show that the developed AB-ResNet is able to recover the spectral function with accuracy comparable to MaxEnt where the noise level is relatively small.
References in corpus (11)
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- Implementation of the Maximum Entropy Method for Analytic Continuation
- Artificial Neural Network Approach to the Analytic Continuation Problem
- Analytic Continuation of Quantum Monte Carlo Data by Stochastic Analytical Inference
- Identifying the maximum entropy method as a special limit of stochastic analytic continuation
- Analytic continuation via domain-knowledge free machine learning
- Multi-level Residual Networks from Dynamical Systems View
- Deep Neural Nets with Interpolating Function as Output Activation
- Fast and Efficient Stochastic Optimization for Analytic Continuation
- Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions
- Model Reduction with Memory and the Machine Learning of Dynamical Systems