The role of data-induced randomness in quantum machine learning classification tasks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Casas, Berta, Bonet-Monroig, Xavier, Pérez-Salinas, Adrián
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915039661785088
author Casas, Berta
Bonet-Monroig, Xavier
Pérez-Salinas, Adrián
author_facet Casas, Berta
Bonet-Monroig, Xavier
Pérez-Salinas, Adrián
contents Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin, by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin, demonstrating that data-induced randomness imposes a limit on classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical tools.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19281
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The role of data-induced randomness in quantum machine learning classification tasks
Casas, Berta
Bonet-Monroig, Xavier
Pérez-Salinas, Adrián
Quantum Physics
Machine Learning
Quantum machine learning (QML) has surged as a prominent area of research with the objective to go beyond the capabilities of classical machine learning models. A critical aspect of any learning task is the process of data embedding, which directly impacts model performance. Poorly designed data-embedding strategies can significantly impact the success of a learning task. Despite its importance, rigorous analyses of data-embedding effects are limited, leaving many cases without effective assessment methods. In this work, we introduce a metric for binary classification tasks, the class margin, by merging the concepts of average randomness and classification margin. This metric analytically connects data-induced randomness with classification accuracy for a given data-embedding map. We benchmark a range of data-embedding strategies through class margin, demonstrating that data-induced randomness imposes a limit on classification performance. We expect this work to provide a new approach to evaluate QML models by their data-embedding processes, addressing gaps left by existing analytical tools.
title The role of data-induced randomness in quantum machine learning classification tasks
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2411.19281