Gaussian Processes for Finite Size Extrapolation of Many-Body Simulations

Abstract

Key to being able to accurately model the properties of realistic materials is being able to predict their properties in the thermodynamic limit. Nevertheless, because most many-body electronic structure methods scale as a high-order polynomial, or even exponentially, with system size, directly simulating large systems in their thermodynamic limit rapidly becomes computationally intractable. As a result, researchers typically estimate the properties of large systems that approach the thermodynamic limit by extrapolating the properties of smaller, computationally-accessible systems based on relatively simple scaling expressions. In this work, we employ Gaussian processes to more accurately and efficiently extrapolate many-body simulations to their thermodynamic limit. We train our Gaussian processes on Smooth Overlap of Atomic Positions (SOAP) descriptors to extrapolate the energies of one-dimensional hydrogen chains obtained using two high-accuracy many-body methods: Coupled Cluster theory and Auxiliary Field Quantum Monte Carlo (AFQMC). In so doing, we show that Gaussian processes trained on relatively short, 10-30-atom chains can predict the energies of both homogeneous and inhomogeneous hydrogen chains in their thermodynamic limit with sub-milliHartree accuracy. Unlike standard scaling expressions, our GPR-based approach is highly generalizable given representative training data and is not dependent on systems' geometries or dimensionality. This work highlights the potential for machine learning to correct for the finite size effects that routinely complicate the interpretation of finite size many-body simulations.

arXiv comment14 pages, 8 figures

References in corpus (56)

• On representing chemical environments
• Machine learning and the physical sciences
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A high-bias, low-variance introduction to Machine Learning for physicists
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Studying Two Dimensional Systems With the Density Matrix Renormalization Group
• Machine learning quantum phases of matter beyond the fermion sign problem
• Twist-averaged Boundary Conditions in Continuum Quantum Monte Carlo
• Quantum Monte Carlo method using phase-free random walks with Slater determinants
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• QMCPACK : An open source ab initio Quantum Monte Carlo package for the electronic structure of atoms, molecules, and solids
• Fermionic neural-network states for ab-initio electronic structure
• Towards the solution of the many-electron problem in real materials: equation of state of the hydrogen chain with state-of-the-art many-body methods
• Finite-size errors in continuum quantum Monte Carlo calculations
• Multireference Correlation in Long Molecules with the Quadratic Scaling Density Matrix Renormalization Group
• Accurate and efficient linear scaling DFT calculations with universal applicability
• Machine-learned multi-system surrogate models for materials prediction
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• Pfaffian pairing wave functions in electronic structure quantum Monte Carlo
• Machine Learning for Quantum Matter
• Ab-initio quantum chemistry with neural-network wavefunctions
• Finite-size correction in many-body electronic structure calculations
• Theory of Finite Size Effects for Electronic Quantum Monte Carlo Calculations of Liquids and Solids
• Pure density functional for strong correlations and the thermodynamic limit from machine learning
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• Strong electronic correlation in the Hydrogen chain: a variational Monte Carlo study
• Ground-state properties of the hydrogen chain: insulator-to-metal transition, dimerization, and magnetic phases
• On Achieving High Accuracy in Quantum Chemical Calculations of 3d Transition Metal Systems: A Comparison of Auxiliary-Field Quantum Monte Carlo with Coupled Cluster, Density Functional Theory, and Experiment for Diatomic Molecules
• Some Recent Developments in Auxiliary-Field Quantum Monte Carlo for Real Materials
• Bond breaking with auxiliary-field quantum Monte Carlo
• Towards the ground state of molecules via diffusion Monte Carlo on neural networks
• Infinite Variance in Fermion Quantum Monte Carlo Calculations
• Quantum Monte Carlo calculations in solids with downfolded Hamiltonians
• An Auxiliary-Field Quantum Monte Carlo Study of the Chromium Dimer
• Transfer learning for scalability of neural-network quantum states
• Stable solid molecular hydrogen above 900K from a machine-learned potential trained with diffusion Quantum Monte Carlo
• Utilizing Essential Symmetry Breaking in Auxiliary-Field Quantum Monte Carlo: Application to the Spin Gaps of the C${}_{36}$ Fullerene and an Iron Porphyrin Model Complex
• Database, Features, and Machine Learning Model to Identify Thermally Driven Metal-Insulator Transition Compounds
• From Tensor Network Quantum States to Tensorial Recurrent Neural Networks
• Systematic study of finite-size effects in quantum Monte Carlo calculations of real metallic systems
• Towards DMC accuracy across chemical space with scalable $\Delta$-QML
• Systematic Comparison and Cross-validation of Fixed-Node Diffusion Monte Carlo and Phaseless Auxiliary-Field Quantum Monte Carlo in Solids
• DeepQMC: an open-source software suite for variational optimization of deep-learning molecular wave functions
• Towards Quantum Monte Carlo Forces on Heavier Ions: Scaling Properties
• Machine Learning Diffusion Monte Carlo Energies
• Gaussian Process States: A data-driven representation of quantum many-body physics
• The quantum Gaussian process state: A kernel-inspired state with quantum support data
• A Bayesian Inference Framework for Compression and Prediction of Quantum States
• Machine learning for a finite size correction in periodic coupled cluster theory calculations
• Neutral band gap of carbon by quantum Monte Carlo methods
• Electronic excitation spectra of molecular hydrogen in Phase I from Quantum Monte Carlo and Many-Body perturbation methods
• $\tilde{O}(N^2)$ Representation of General Continuous Anti-symmetric Function