Density Matrix Classifier

18 Pages Posted: 3 Dec 2024

See all articles by David Garvin

David Garvin

Rigetti Computing

Oleksiy Kondratyev

Imperial College London - Department of Mathematics

Alexander Lipton

Abu Dhabi Investment Authority

Marco Paini

Rigetti Computing

Date Written: November 08, 2024

Abstract

We introduce a new type of quantum machine learning classifier based on the estimation of the Frobenius distance between density matrices. The central idea is to encode all samples in the dataset belonging to a particular class into a corresponding density matrix using the quantum feature map methodology. The same quantum feature map is used to encode every new test sample into its own corresponding density matrix. The Frobenius distances between the sample density matrix and the density matrices encoding all classes present in the training dataset are calculated. The class label is assigned by selecting the class with minimum distance. The density matrix classifier uses parameterised quantum circuits. On the Glass Identification dataset, it performed on par with, or sometimes exceeded, performance of standard classical classifiers including multi-layer perceptron, random forest, support vector machine, and logistic regression. The model is resistant to certain types of noise and is suitable for execution on NISQ computers.

Suggested Citation

Garvin, David and Kondratyev, Oleksiy and Lipton, Alexander and Paini, Marco, Density Matrix Classifier (November 08, 2024). Available at SSRN: https://ssrn.com/abstract=5014387 or http://dx.doi.org/10.2139/ssrn.5014387

David Garvin

Rigetti Computing

Oleksiy Kondratyev (Contact Author)

Imperial College London - Department of Mathematics ( email )

South Kensington Campus
Imperial College
LONDON, SW7 2AZ
United Kingdom

Alexander Lipton

Abu Dhabi Investment Authority

Marco Paini

Rigetti Computing ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
89
Abstract Views
384
Rank
624,259
PlumX Metrics