Advancing Machine Learning Applications in Quantum Few-Body Systems

TL;DR

This paper introduces a neural network framework that accurately models quantum few-body systems, handling diverse configurations and scaling efficiently, thus providing a versatile tool for quantum physics research.

Contribution

The authors develop a flexible neural network approach combining adaptive step size and Monte Carlo sampling, capable of modeling various quantum few-body systems with improved accuracy and scalability.

Findings

Achieves lower energy errors than previous ML methods.

Scales favorably with system size using GPU acceleration.

Captures spatial and correlation structures for physical insights.

Abstract

This paper presents a general neural network framework for solving quantum few-body systems, extending prior methods to handle diverse particle masses, interaction types, and system configurations. Our architecture, which combines an adaptive step size with the Metropolis-Adjusted Langevin Algorithm for Monte Carlo sampling, accurately approximates the ground-state wave functions of systems featuring harmonic confinement, Gaussian two-body interactions, and including three-body forces. In ten-particle systems, it achieves lower relative energy errors (with respect to the reference values) than previous machine-learning methods. Leveraging GPU-accelerated computation, the method scales favorably with system size while maintaining robust convergence, reduced hyperparameter sensitivity, and stable training. Beyond accurate energy estimation, the model captures spatial distributions and correlation structures, offering physical insights about inter-particle structure. By unifying applicability across identical and nonidentical particles, the proposed approach establishes a versatile computational tool for exploring complex few-body quantum systems, with significant implications for advancing computational models in few-body quantum systems.