Machine Learning based Discrimination for Excited State Promoted Readout

TL;DR

This paper explores the use of machine learning algorithms, including deep neural networks and classical classifiers, to improve the fidelity of excited state promoted readout in superconducting qubits, demonstrating enhanced discrimination performance.

Contribution

It introduces the application of various machine learning techniques to quantum readout, comparing their effectiveness and robustness against traditional methods on IBM's quantum hardware.

Findings

Deep neural networks improve qubit state discrimination fidelity.

Machine learning methods show robustness to readout crosstalk.

Compared algorithms differ in training time and accuracy.

Abstract

A limiting factor for readout fidelity for superconducting qubits is the relaxation of the qubit to the ground state before the time needed for the resonator to reach its final target state. A technique known as excited state promoted (ESP) readout was proposed to reduce this effect and further improve the readout contrast on superconducting hardware. In this work, we use readout data from IBM's five-qubit quantum systems to measure the effectiveness of using deep neural networks, like feedforward neural networks, and various classification algorithms, like k-nearest neighbors, decision trees, and Gaussian naive Bayes, for single-qubit and multi-qubit discrimination. These methods were compared to standardly used linear and quadratic discriminant analysis algorithms based on their qubit-state-assignment fidelity performance, robustness to readout crosstalk, and training time.