Spin-qubit noise spectroscopy from randomized benchmarking by supervised learning

TL;DR

This paper introduces a supervised learning approach to extract $1/f$ noise spectra from randomized benchmarking data in spin-qubit devices, providing accurate noise exponent and amplitude predictions as an alternative measurement method.

Contribution

The study presents a novel neural network-based method to determine noise spectra from randomized benchmarking, achieving high accuracy in predicting noise parameters.

Findings

Neural networks predict noise exponent with ~0.05 error.

Noise amplitude can be estimated with 5% error if the exponent is known.

Method offers an alternative to traditional noise spectrum measurement.

Abstract

We demonstrate a method to obtain the spectra of $1/f$ noises in spin-qubit devices from randomized benchmarking, assisted by supervised learning. The noise exponent, which indicates the correlation within the noise, is determined by training a double-layer neural network with the ratio between the randomized benchmarking results of pulse sequences that correct noise and not. After the training is completed, the neural network is able to predict the exponent within an absolute error of about 0.05, comparable with existing methods. The noise amplitude is then evaluated by training another neural network with the decaying fidelity of randomized benchmarking results from the uncorrected sequences. The relative error for the prediction of the noise amplitude is as low as 5\% provided that the noise exponent is known. Our results suggest that the neural network is capable of predicting noise spectra from randomized benchmarking, which can be an alternative method to measure noise spectra in spin-qubit devices.