Potential and limitations of random Fourier features for dequantizing quantum machine learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sweke, Ryan, Recio-Armengol, Erik, Jerbi, Sofiene, Gil-Fuster, Elies, Fuller, Bryce, Eisert, Jens, Meyer, Johannes Jakob
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908273297326080
author Sweke, Ryan
Recio-Armengol, Erik
Jerbi, Sofiene
Gil-Fuster, Elies
Fuller, Bryce
Eisert, Jens
Meyer, Johannes Jakob
author_facet Sweke, Ryan
Recio-Armengol, Erik
Jerbi, Sofiene
Gil-Fuster, Elies
Fuller, Bryce
Eisert, Jens
Meyer, Johannes Jakob
contents Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where parameterized quantum circuits (PQCs) are used as learning models. These PQC models have a rich structure which suggests that they might be amenable to efficient dequantization via random Fourier features (RFF). In this work, we establish necessary and sufficient conditions under which RFF does indeed provide an efficient dequantization of variational quantum machine learning for regression. We build on these insights to make concrete suggestions for PQC architecture design, and to identify structures which are necessary for a regression problem to admit a potential quantum advantage via PQC based optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11647
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Potential and limitations of random Fourier features for dequantizing quantum machine learning
Sweke, Ryan
Recio-Armengol, Erik
Jerbi, Sofiene
Gil-Fuster, Elies
Fuller, Bryce
Eisert, Jens
Meyer, Johannes Jakob
Quantum Physics
Machine Learning
Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where parameterized quantum circuits (PQCs) are used as learning models. These PQC models have a rich structure which suggests that they might be amenable to efficient dequantization via random Fourier features (RFF). In this work, we establish necessary and sufficient conditions under which RFF does indeed provide an efficient dequantization of variational quantum machine learning for regression. We build on these insights to make concrete suggestions for PQC architecture design, and to identify structures which are necessary for a regression problem to admit a potential quantum advantage via PQC based optimization.
title Potential and limitations of random Fourier features for dequantizing quantum machine learning
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2309.11647