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.
@article{arxiv.2107.12975,
title = {Cross-architecture Tuning of Silicon and SiGe-based Quantum Devices Using Machine Learning},
author = {B. Severin and D. T. Lennon and L. C. Camenzind and F. Vigneau and F. Fedele and D. Jirovec and A. Ballabio and D. Chrastina and G. Isella and M. de Kruijf and M. J. Carballido and S. Svab and A. V. Kuhlmann and F. R. Braakman and S. Geyer and F. N. M. Froning and H. Moon and M. A. Osborne and D. Sejdinovic and G. Katsaros and D. M. Zumbühl and G. A. D. Briggs and N. Ares},
journal= {arXiv preprint arXiv:2107.12975},
year = {2024}
}