Method for noise-induced regularization in quantum neural networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kuzmin, Viacheslav, Somogyi, Wilfrid, Pankovets, Ekaterina, Melnikov, Alexey
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910023663222784
author Kuzmin, Viacheslav
Somogyi, Wilfrid
Pankovets, Ekaterina
Melnikov, Alexey
author_facet Kuzmin, Viacheslav
Somogyi, Wilfrid
Pankovets, Ekaterina
Melnikov, Alexey
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19921
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Method for noise-induced regularization in quantum neural networks
Kuzmin, Viacheslav
Somogyi, Wilfrid
Pankovets, Ekaterina
Melnikov, Alexey
Quantum Physics
Machine Learning
Neural and Evolutionary Computing
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.
title Method for noise-induced regularization in quantum neural networks
topic Quantum Physics
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2410.19921