The quantum cost function concentration dependency on the parametrization expressivity
This work addresses a foundational issue in quantum machine learning for researchers, providing insights into resource requirements, but it is incremental as it builds on existing quantum variational circuit strategies.
The study tackles the problem of understanding the minimum resources needed for quantum machine learning models by analyzing how the expressiveness of parametrization in quantum variational circuits affects the cost function, showing analytically that more expressive parametrization leads to cost function concentration around a value dependent on observable and qubit count, with numerical simulations confirming the predictions.
Although we are currently in the era of noisy intermediate scale quantum devices, several studies are being conducted with the aim of bringing machine learning to the quantum domain. Currently, quantum variational circuits are one of the main strategies used to build such models. However, despite its widespread use, we still do not know what are the minimum resources needed to create a quantum machine learning model. In this article, we analyze how the expressiveness of the parametrization affects the cost function. We analytically show that the more expressive the parametrization is, the more the cost function will tend to concentrate around a value that depends both on the chosen observable and on the number of qubits used. For this, we initially obtain a relationship between the expressiveness of the parametrization and the mean value of the cost function. Afterwards, we relate the expressivity of the parametrization with the variance of the cost function. Finally, we show some numerical simulation results that confirm our theoretical-analytical predictions. To the best of our knowledge, this is the first time that these two important aspects of quantum neural networks are explicitly connected.