Geometrical versus time-series representation of data in quantum control learning

TL;DR

This paper compares geometrical and time-series data representations in quantum control learning, showing geometrical methods can achieve high fidelity and neural networks offer better generalization in variable disturbance scenarios.

Contribution

It demonstrates the effectiveness of geometrical data representation in quantum control and highlights the generalization advantage of neural networks over geometrical methods.

Findings

Geometrical data representation achieves high-fidelity quantum control.

Neural networks can generalize control pulses for systems with variable disturbances.

Geometrical methods are competitive with complex approaches in certain scenarios.

Abstract

Recently machine learning techniques have become popular for analysing physical systems and solving problems occurring in quantum computing. In this paper we focus on using such techniques for finding the sequence of physical operations implementing the given quantum logical operation. In this context we analyse the flexibility of the data representation and compare the applicability of two machine learning approaches based on different representations of data. We demonstrate that the utilization of the geometrical structure of control pulses is sufficient for achieving high-fidelity of the implemented evolution. We also demonstrate that artificial neural networks, unlike geometrical methods, posses the generalization abilities enabling them to generate control pulses for the systems with variable strength of the disturbance. The presented results suggest that in some quantum control scenarios, geometrical data representation and processing is competitive to more complex methods.