Quantum k-fold cross-validation for nearest neighbor classification algorithm

Cross-validation is one of the important tools in machine learning, which is generally used for performance evaluation. It uses different portions of the data to test and train a model on different iterations, which leads to a high computational cost. In this paper, we present a quantum version of k...

Full description

Saved in:
Bibliographic Details
Published in:Physica A Vol. 611; p. 128435
Main Authors: Li, Jing, Gao, Fei, Lin, Song, Guo, Mingchao, Li, Yongmei, Liu, Hailing, Qin, Sujuan, Wen, QiaoYan
Format: Journal Article
Language:English
Published: Elsevier B.V 01.02.2023
Subjects:
Cross-validation
Quantum computing
Quantum machine learning
Quantum nearest neighbor algorithm
Quantum computing
Quantum machine learning
Cross-validation
Quantum nearest neighbor algorithm
ISSN:0378-4371, 1873-2119
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cross-validation is one of the important tools in machine learning, which is generally used for performance evaluation. It uses different portions of the data to test and train a model on different iterations, which leads to a high computational cost. In this paper, we present a quantum version of k-fold cross-validation to choose a good parameter for the nearest neighbor classification algorithm with a threshold t, where the classification performance is estimated efficiently. With the help of amplitude amplification and estimation, the proposed quantum algorithm achieves a polynomial speedup on the number of samples over its classical counterpart. •A quantum k-fold cross-validation is proposed to choose a good parameter for the NN classifier efficiently.•The proposed quantum algorithm achieves a polynomial speedup over its classical counterpart.•A modified quantum NN classifier with a threshold t is presented.
ISSN:0378-4371
1873-2119
DOI:10.1016/j.physa.2022.128435