Dequantizing quantum machine learning models using tensor networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shin, Seongwook, Teo, Yong Siah, Jeong, Hyunseok
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914848906936320
author Shin, Seongwook
Teo, Yong Siah
Jeong, Hyunseok
author_facet Shin, Seongwook
Teo, Yong Siah
Jeong, Hyunseok
contents Ascertaining whether a classical model can efficiently replace a given quantum model -- dequantization -- is crucial in assessing the true potential of quantum algorithms. In this work, we introduced the dequantizability of the function class of variational quantum-machine-learning~(VQML) models by employing the tensor network formalism, effectively identifying every VQML model as a subclass of matrix product state (MPS) model characterized by constrained coefficient MPS and tensor product-based feature maps. From this formalism, we identify the conditions for which a VQML model's function class is dequantizable or not. Furthermore, we introduce an efficient quantum kernel-induced classical kernel which is as expressive as given any quantum kernel, hinting at a possible way to dequantize quantum kernel methods. This presents a thorough analysis of VQML models and demonstrates the versatility of our tensor-network formalism to properly distinguish VQML models according to their genuine quantum characteristics, thereby unifying classical and quantum machine-learning models within a single framework.
format Preprint
id arxiv_https___arxiv_org_abs_2307_06937
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Dequantizing quantum machine learning models using tensor networks
Shin, Seongwook
Teo, Yong Siah
Jeong, Hyunseok
Quantum Physics
Ascertaining whether a classical model can efficiently replace a given quantum model -- dequantization -- is crucial in assessing the true potential of quantum algorithms. In this work, we introduced the dequantizability of the function class of variational quantum-machine-learning~(VQML) models by employing the tensor network formalism, effectively identifying every VQML model as a subclass of matrix product state (MPS) model characterized by constrained coefficient MPS and tensor product-based feature maps. From this formalism, we identify the conditions for which a VQML model's function class is dequantizable or not. Furthermore, we introduce an efficient quantum kernel-induced classical kernel which is as expressive as given any quantum kernel, hinting at a possible way to dequantize quantum kernel methods. This presents a thorough analysis of VQML models and demonstrates the versatility of our tensor-network formalism to properly distinguish VQML models according to their genuine quantum characteristics, thereby unifying classical and quantum machine-learning models within a single framework.
title Dequantizing quantum machine learning models using tensor networks
topic Quantum Physics
url https://arxiv.org/abs/2307.06937