Method for noise-induced regularization in quantum neural networks

TL;DR

This paper introduces a noise tuning method for quantum neural networks that enhances their generalization ability, acting as a form of regularization, and demonstrates its effectiveness through regression tasks and simulations on realistic quantum hardware.

Contribution

It proposes a novel noise tuning technique that improves quantum neural network generalization, supported by numerical experiments and simulations on superconducting quantum computers.

Findings

Noise tuning improves quantum neural network generalization.

Validation mean squared error decreases with optimal noise levels.

Method is effective on realistic noisy quantum hardware simulations.

Abstract

In the current quantum computing paradigm, significant focus is placed on the reduction or mitigation of quantum decoherence. When designing new quantum processing units, the general objective is to reduce the amount of noise qubits are subject to, and in algorithm design, a large effort is underway to provide scalable error correction or mitigation techniques. Yet some previous work has indicated that certain classes of quantum algorithms, such as quantum machine learning, may, in fact, be intrinsically robust to or even benefit from the presence of a small amount of noise. Here, we demonstrate that noise levels in quantum hardware can be effectively tuned to enhance the ability of quantum neural networks to generalize data, acting akin to regularisation in classical neural networks. As an example, we consider two regression tasks, where, by tuning the noise level in the circuit, we demonstrated improvement of the validation mean squared error loss. Moreover, we demonstrate the method's effectiveness by numerically simulating quantum neural network training on a realistic model of a noisy superconducting quantum computer.