Bridging the Gap between Deep Learning and Frustrated Quantum Spin System for Extreme-scale Simulations on New Generation of Sunway Supercomputer

Abstract

Efficient numerical methods are promising tools for delivering unique insights into the fascinating properties of physics, such as the highly frustrated quantum many-body systems. However, the computational complexity of obtaining the wave functions for accurately describing the quantum states increases exponentially with respect to particle number. Here we present a novel convolutional neural network (CNN) for simulating the two-dimensional highly frustrated spin-$1/2$ $J_1-J_2$ Heisenberg model, meanwhile the simulation is performed at an extreme scale system with low cost and high scalability. By ingenious employment of transfer learning and CNN's translational invariance, we successfully investigate the quantum system with the lattice size up to $24\times 24$, within 30 million cores of the new generation of sunway supercomputer. The final achievement demonstrates the effectiveness of CNN-based representation of quantum-state and brings the state-of-the-art record up to a brand-new level from both aspects of remarkable accuracy and unprecedented scales.

This paper reviews the technical details of calculating spin-1/2 J1-J2 model using convolutional neural network ansatz on Sunway Supercomputer

References in corpus (8)

• Large Batch Training of Convolutional Networks
• Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
• Dirac-type nodal spin liquid revealed by refined quantum many-body solver using neural-network wave function, correlation ratio, and level spectroscopy
• Neural network wave functions and the sign problem
• Hybrid convolutional neural network and PEPS wave functions for quantum many-particle states
• Chiral spin states in the pyrochlore Heisenberg magnet: Fermionic mean-field theory and variational Monte Carlo calculations
• Scalable Second Order Optimization for Deep Learning
• Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation