Machine Learning based Discrimination for Excited State Promoted Readout
This work addresses readout fidelity issues in quantum computing, but it is incremental as it applies existing ML methods to a known technique without introducing new paradigms.
The paper tackled the problem of improving readout fidelity in superconducting qubits by applying machine learning classifiers to excited state promoted readout data from IBM's five-qubit systems, achieving enhanced discrimination performance compared to standard methods.
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.