What is my quantum computer good for? Quantum capability learning with physics-aware neural networks

TL;DR

This paper introduces a physics-aware neural network architecture that effectively models quantum computer capabilities, significantly improving accuracy over previous models by incorporating quantum physics insights.

Contribution

The authors develop a novel quantum-physics-aware neural network that combines graph neural networks with physics approximations to better predict quantum computer performance.

Findings

Achieves up to 50% reduction in mean absolute error

Outperforms state-of-the-art convolutional neural networks

Validates on both experimental and simulated data

Abstract

Quantum computers have the potential to revolutionize diverse fields, including quantum chemistry, materials science, and machine learning. However, contemporary quantum computers experience errors that often cause quantum programs run on them to fail. Until quantum computers can reliably execute large quantum programs, stakeholders will need fast and reliable methods for assessing a quantum computer's capability-i.e., the programs it can run and how well it can run them. Previously, off-the-shelf neural network architectures have been used to model quantum computers' capabilities, but with limited success, because these networks fail to learn the complex quantum physics that determines real quantum computers' errors. We address this shortcoming with a new quantum-physics-aware neural network architecture for learning capability models. Our architecture combines aspects of graph neural networks with efficient approximations to the physics of errors in quantum programs. This approach achieves up to $\sim50\%$ reductions in mean absolute error on both experimental and simulated data, over state-of-the-art models based on convolutional neural networks.