Quantum device fine-tuning using unsupervised embedding learning
This addresses the problem of efficient parameter control in quantum devices for researchers and engineers, representing an incremental improvement with a specific application.
The paper tackles the challenge of fine-tuning multiple parameters in quantum devices with many gate electrodes by experimentally demonstrating an unsupervised algorithm that uses a variational auto-encoder to score measurements and optimize gate voltages in real-time, achieving fine-tuning times of about 40 minutes for a double quantum dot device.
Quantum devices with a large number of gate electrodes allow for precise control of device parameters. This capability is hard to fully exploit due to the complex dependence of these parameters on applied gate voltages. We experimentally demonstrate an algorithm capable of fine-tuning several device parameters at once. The algorithm acquires a measurement and assigns it a score using a variational auto-encoder. Gate voltage settings are set to optimise this score in real-time in an unsupervised fashion. We report fine-tuning times of a double quantum dot device within approximately 40 min.