Quantum-tailored machine-learning characterization of a superconducting qubit

TL;DR

This paper presents a physics-inspired machine learning method that effectively characterizes a superconducting qubit's dynamics, outperforming generic models by incorporating quantum mechanics features for improved accuracy and efficiency.

Contribution

The work introduces a quantum-tailored ML approach that leverages domain knowledge to enhance device characterization over traditional physics-agnostic models.

Findings

Outperforms generic recurrent neural networks in qubit characterization

Requires less data for accurate device parameter learning

Demonstrates improved scalability for quantum device diagnostics

Abstract

Machine learning (ML) is a promising approach for performing challenging quantum-information tasks such as device characterization, calibration and control. ML models can train directly on the data produced by a quantum device while remaining agnostic to the quantum nature of the learning task. However, these generic models lack physical interpretability and usually require large datasets in order to learn accurately. Here we incorporate features of quantum mechanics in the design of our ML approach to characterize the dynamics of a quantum device and learn device parameters. This physics-inspired approach outperforms physics-agnostic recurrent neural networks trained on numerically generated and experimental data obtained from continuous weak measurement of a driven superconducting transmon qubit. This demonstration shows how leveraging domain knowledge improves the accuracy and efficiency of this characterization task, thus laying the groundwork for more scalable characterization techniques.