Active Learning Algorithm for Computational Physics

Abstract

In large-scale computation of physics problems, one often encounters the problem of determining a multi-dimensional function, which can be time-consuming when computing each point in this multi-dimensional space is already time-demanding. In the work, we propose that the active learning algorithm can speed up such calculations. The basic idea is to fit a multi-dimensional function by neural networks, and the key point is to make the query of labeled data economically by using a stratagem called "query by committee". We present the general protocol of this fitting scheme, as well as the procedure of how to further compute physical observables with the fitted functions. We show that this method can work well with two examples, which are quantum three-body problem in atomic physics and the anomalous Hall conductivity in condensed matter physics, respectively. In these examples, we show that one reaches an accuracy of few percent error for computing physical observables with less than $10\%$ of total data points compared with uniform sampling. With these two examples, we also visualize that by using the active learning algorithm, the required data are added mostly in the regime where the function varies most rapidly, which explains the mechanism for the efficiency of the algorithm. We expect broad applications of our method on various kind of computational physics problems.

arXiv comment7 pages, 8 figures

References in corpus (29)

• Berry Phase Effects on Electronic Properties
• Wannier90: A Tool for Obtaining Maximally-Localised Wannier Functions
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Universality in Few-body Systems with Large Scattering Length
• A high-bias, low-variance introduction to Machine Learning for physicists
• Large anomalous Hall effect driven by non-vanishing Berry curvature in non-collinear antiferromagnetic Mn3Ge
• Less is more: sampling chemical space with active learning
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Topological Weyl semimetals in the chiral antiferromagnetic materials Mn3Ge and Mn3Sn
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Machine Learning Topological States
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Approximating quantum many-body wave-functions using artificial neural networks
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Machine learning of quantum phase transitions
• Self-learning Monte Carlo with Deep Neural Networks
• Method to solve quantum few-body problems with artificial neural networks
• Approaching the adiabatic timescale with machine-learning
• Accelerated Continuous time quantum Monte Carlo method with Machine Learning

Cited by in corpus (8)

• Taming nuclear complexity with a committee of multilayer neural networks
• Adaptive Quantum State Tomography with Active Learning
• Efficient Learning of a One-dimensional Density Functional Theory
• Active Learning Approach to Optimization of Experimental Control
• Preparing Quantum States by Measurement-feedback Control with Bayesian Optimization
• Active Learning in Physics: From 101, to Progress, and Perspective
• Quantum Active Learning
• Active Learning for Quantum Mechanical Measurements