Using Neural Networks in Determinant Quantum Monte Carlo to study the Holstein Model.*

Machine learning techniques have recently occupied the focus of many investigators in computational many-body physics.  In particular, some practitioners of quantum Monte-Carlo have considered the efficacy of various "Self-Learning'' techniques which aim to reduce CPU runtime associated with updates and autocorrelation.  In this talk, I will discuss our group's efforts to use artificial neural networks (NN) within determinant quantum Monte-Carlo (DQMC) to improve the scaling of CPU runtime with typical system parameters.  This work has focused primarily on the singleband Holstein model, which is, perhaps, the simplest model for studying electron-phonon coupling in many body systems.  We have explored both fully connected and convolutional NN and used them to study the metallic and insulating phases of the Holstein model.  Looking forward, NN-DQMC is well suited for studying not only the Holstein model but extensions thereof.