Cross-architecture Tuning of Silicon and SiGe-based Quantum Devices Using Machine Learning

TL;DR

This paper demonstrates a machine learning algorithm capable of efficiently tuning various silicon and SiGe-based quantum devices, significantly reducing tuning times and providing insights into device parameter landscapes.

Contribution

The paper introduces a versatile machine learning-based tuning algorithm applicable across different quantum device architectures without modifications.

Findings

Achieved tuning times of 30, 10, and 92 minutes for different devices.

Successfully tuned multiple device types from scratch.

Provided insights into device parameter space landscapes.

Abstract

The potential of Si and SiGe-based devices for the scaling of quantum circuits is tainted by device variability. Each device needs to be tuned to operation conditions. We give a key step towards tackling this variability with an algorithm that, without modification, is capable of tuning a 4-gate Si FinFET, a 5-gate GeSi nanowire and a 7-gate SiGe heterostructure double quantum dot device from scratch. We achieve tuning times of 30, 10, and 92 minutes, respectively. The algorithm also provides insight into the parameter space landscape for each of these devices. These results show that overarching solutions for the tuning of quantum devices are enabled by machine learning.