# American Institute of Mathematical Sciences

doi: 10.3934/dcdss.2021088
Online First

Online First articles are published articles within a journal that have not yet been assigned to a formal issue. This means they do not yet have a volume number, issue number, or page numbers assigned to them, however, they can still be found and cited using their DOI (Digital Object Identifier). Online First publication benefits the research community by making new scientific discoveries known as quickly as possible.

Readers can access Online First articles via the “Online First” tab for the selected journal.

## Analytic continuation of noisy data using Adams Bashforth residual neural network

 1 New York University, New York, NY, 10012 2 Florida State University, Tallahassee, FL, 32304 3 Oak Ridge National Laboratory, Oak Ridge, TN, 37830 4 University of Tennessee-Knoxville, Knoxville, TN, 37916

* Corresponding author

Received  February 2021 Revised  April 2021 Early access August 2021

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.

Citation: Xuping Xie, Feng Bao, Thomas Maier, Clayton Webster. Analytic continuation of noisy data using Adams Bashforth residual neural network. Discrete & Continuous Dynamical Systems - S, doi: 10.3934/dcdss.2021088
##### References:

show all references

##### References:
Illustration of data-driven learning framework for analytic continuation
Single hidden layer neural network structure
Residual neural network block
Multistep neural network architecture
One data sample from the training set $G(\tau)$ (top left), Legendre representation $G_l$ (top right), and target spectral density $A(\omega)$ (bottom)
The training performance from AB1-ResNet, AB2-ResNet, and AB3-ResNet structure with data noise $10^{-2}$
Three different spectral density function $A(\omega)$ generated from AB3-ResNet and Maxent (dark line). The left column represents results from dataset with noise level $10^{-2}$, the right column shows results obtained from the dataset under noise level $10^{-3}$
The comparison of predicted spectral function between different AB-ResNet
 [1] Feng Bao, Thomas Maier. Stochastic gradient descent algorithm for stochastic optimization in solving analytic continuation problems. Foundations of Data Science, 2020, 2 (1) : 1-17. doi: 10.3934/fods.2020001 [2] Weishi Yin, Jiawei Ge, Pinchao Meng, Fuheng Qu. A neural network method for the inverse scattering problem of impenetrable cavities. Electronic Research Archive, 2020, 28 (2) : 1123-1142. doi: 10.3934/era.2020062 [3] King Hann Lim, Hong Hui Tan, Hendra G. Harno. Approximate greatest descent in neural network optimization. Numerical Algebra, Control & Optimization, 2018, 8 (3) : 327-336. doi: 10.3934/naco.2018021 [4] David W. Pravica, Michael J. Spurr. Analytic continuation into the future. Conference Publications, 2003, 2003 (Special) : 709-716. doi: 10.3934/proc.2003.2003.709 [5] Hyeontae Jo, Hwijae Son, Hyung Ju Hwang, Eun Heui Kim. Deep neural network approach to forward-inverse problems. Networks & Heterogeneous Media, 2020, 15 (2) : 247-259. doi: 10.3934/nhm.2020011 [6] Hui-Qiang Ma, Nan-Jing Huang. Neural network smoothing approximation method for stochastic variational inequality problems. Journal of Industrial & Management Optimization, 2015, 11 (2) : 645-660. doi: 10.3934/jimo.2015.11.645 [7] Hongtruong Pham, Xiwen Lu. The inverse parallel machine scheduling problem with minimum total completion time. Journal of Industrial & Management Optimization, 2014, 10 (2) : 613-620. doi: 10.3934/jimo.2014.10.613 [8] Cheng-Dar Liou. Optimization analysis of the machine repair problem with multiple vacations and working breakdowns. Journal of Industrial & Management Optimization, 2015, 11 (1) : 83-104. doi: 10.3934/jimo.2015.11.83 [9] Fengqiu Liu, Xiaoping Xue. Subgradient-based neural network for nonconvex optimization problems in support vector machines with indefinite kernels. Journal of Industrial & Management Optimization, 2016, 12 (1) : 285-301. doi: 10.3934/jimo.2016.12.285 [10] Lucie Baudouin, Emmanuelle Crépeau, Julie Valein. Global Carleman estimate on a network for the wave equation and application to an inverse problem. Mathematical Control & Related Fields, 2011, 1 (3) : 307-330. doi: 10.3934/mcrf.2011.1.307 [11] Xiaoli Feng, Meixia Zhao, Peijun Li, Xu Wang. An inverse source problem for the stochastic wave equation. Inverse Problems & Imaging, , () : -. doi: 10.3934/ipi.2021055 [12] Yi-Kuei Lin, Cheng-Ta Yeh. Reliability optimization of component assignment problem for a multistate network in terms of minimal cuts. Journal of Industrial & Management Optimization, 2011, 7 (1) : 211-227. doi: 10.3934/jimo.2011.7.211 [13] Émilie Chouzenoux, Henri Gérard, Jean-Christophe Pesquet. General risk measures for robust machine learning. Foundations of Data Science, 2019, 1 (3) : 249-269. doi: 10.3934/fods.2019011 [14] Ana Rita Nogueira, João Gama, Carlos Abreu Ferreira. Causal discovery in machine learning: Theories and applications. Journal of Dynamics & Games, 2021, 8 (3) : 203-231. doi: 10.3934/jdg.2021008 [15] Jianfeng Feng, Mariya Shcherbina, Brunello Tirozzi. Stability of the dynamics of an asymmetric neural network. Communications on Pure & Applied Analysis, 2009, 8 (2) : 655-671. doi: 10.3934/cpaa.2009.8.655 [16] Lekbir Afraites, Chorouk Masnaoui, Mourad Nachaoui. Shape optimization method for an inverse geometric source problem and stability at critical shape. Discrete & Continuous Dynamical Systems - S, 2021  doi: 10.3934/dcdss.2021006 [17] Li-Fang Dai, Mao-Lin Liang, Wei-Yuan Ma. Optimization problems on the rank of the solution to left and right inverse eigenvalue problem. Journal of Industrial & Management Optimization, 2015, 11 (1) : 171-183. doi: 10.3934/jimo.2015.11.171 [18] Yuk L. Yung, Cameron Taketa, Ross Cheung, Run-Lie Shia. Infinite sum of the product of exponential and logarithmic functions, its analytic continuation, and application. Discrete & Continuous Dynamical Systems - B, 2010, 13 (1) : 229-248. doi: 10.3934/dcdsb.2010.13.229 [19] Jan Boman. Unique continuation of microlocally analytic distributions and injectivity theorems for the ray transform. Inverse Problems & Imaging, 2010, 4 (4) : 619-630. doi: 10.3934/ipi.2010.4.619 [20] Ndolane Sene. Fractional input stability and its application to neural network. Discrete & Continuous Dynamical Systems - S, 2020, 13 (3) : 853-865. doi: 10.3934/dcdss.2020049

2020 Impact Factor: 2.425

## Tools

Article outline

Figures and Tables