Work

Spacetime Neural Network for High Dimensional Quantum Dynamics

Year: 2021

Type: preprint

Abstract: We develop a spacetime neural network method with second order optimization for solving quantum dynamics from the high dimensional Schrödinger equation. In contrast to the standard iterative first order optimization and the time-dependent variational principle, our approach utilizes the implicit mid-point method and generates the solution for all spatial and temporal values simultaneously after optimization. We demonstrate the method in the Schrödinger equation with a self-normalized autoregressive spacetime neural network construction. Future explorations for solving different high dimensional differential equations are discussed.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2108.02200

Authors: Wang, Jiangran, Chen, Zhuo, Luo, Di, Zhao, Zhizhen, Hur, Vera Mikyoung, Clark, Bryan K.

Institutions: University of Illinois Urbana-Champaign, National Center for Supercomputing Applications, Anthony J. Leggett Institute for Condensed Matter Theory

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy, Alfred P. Sloan Foundation, University of Illinois at Urbana-Champaign

Awards: MRI: Development of an Instrument for Deep Learning Research, Collaborative Research: Advancing Science with Accelerated Machine Learning, Breaking, Peaking, and Disintegration, G4929652472, PORTING CLASSICAL APPROACHES FOR QUANTUM SIMULATIONS TO QUANTUM COMPUTERS, G7388224766

OpenAlex ID: W3192954975

Cites: 16

Cited by: 6

Related to: 10