Machine learning enables completely automatic tuning of a quantum device faster than human experts

Abstract

Variability is a problem for the scalability of semiconductor quantum devices. The parameter space is large, and the operating range is small. Our statistical tuning algorithm searches for specific electron transport features in gate-defined quantum dot devices with a gate voltage space of up to eight dimensions. Starting from the full range of each gate voltage, our machine learning algorithm can tune each device to optimal performance in a median time of under 70 minutes. This performance surpassed our best human benchmark (although both human and machine performance can be improved). The algorithm is approximately 180 times faster than an automated random search of the parameter space, and is suitable for different material systems and device architectures. Our results yield a quantitative measurement of device variability, from one device to another and after thermal cycling. Our machine learning algorithm can be extended to higher dimensions and other technologies.

Deep reinforcement learning for efficient measurement of quantum devices

“…1a. We ran the DRL algorithm in two different regions of gate voltage space, I and II, which are centred in the coordinates from our super coarse tuning algorithm 36 . We ran the algorithm ten times in each region.…”

“…However, quantum dot devices are subject to variability, and many measurements are required to characterise each device and find the conditions for qubit operation. Machine learning has been used to automate the tuning of devices from scratch, known as super coarse tuning [34][35][36] , the identification of single or double quantum dot regimes, known as coarse tuning 37,38 , and the tuning of the inter-dot tunnel couplings and other device parameters, referred to as fine tuning [39][40][41] .…”

“…1b. A super coarse tuning algorithm allows us to choose a set of promising gate voltages and focus on exploring the current map as a function of two gates, for example the two barrier gates 36 . This is the gate voltage space our DRL agent will navigate.…”

“…Our DRL algorithm takes the gate voltage coordinates found by our previous super coarse tuning algorithm 36 , and divides the gate voltage space corresponding to the unmeasured current map into blocks. The size of the blocks is chosen such that they can fully contain bias triangles (blocks are shown as a white grid in Fig.…”

Simultaneous operation of singlet-triplet qubits

“…Overall, our results suggest that large quantum dots may prove useful as tunable inter-qubit couplers to realize two-dimensional qubit networks. However, the large number of gate voltages that need to be tuned and synchronized is currently challenging for our manual tuneup procedures, and motivates the development of superhuman automation 36 .…”