Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kölle, Michael, Ahouzi, Afrae, Debus, Pascal, Çetiner, Elif, Müller, Robert, Schuman, Daniëlle, Linnhoff-Popien, Claudia
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.20753
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909274207158272
author Kölle, Michael
Ahouzi, Afrae
Debus, Pascal
Çetiner, Elif
Müller, Robert
Schuman, Daniëlle
Linnhoff-Popien, Claudia
author_facet Kölle, Michael
Ahouzi, Afrae
Debus, Pascal
Çetiner, Elif
Müller, Robert
Schuman, Daniëlle
Linnhoff-Popien, Claudia
contents Quantum one-class support vector machines leverage the advantage of quantum kernel methods for semi-supervised anomaly detection. However, their quadratic time complexity with respect to data size poses challenges when dealing with large datasets. In recent work, quantum randomized measurements kernels and variable subsampling were proposed, as two independent methods to address this problem. The former achieves higher average precision, but suffers from variance, while the latter achieves linear complexity to data size and has lower variance. The current work focuses instead on combining these two methods, along with rotated feature bagging, to achieve linear time complexity both to data size and to number of features. Despite their instability, the resulting models exhibit considerably higher performance and faster training and testing times.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Quantum One-Class Support Vector Machines for Anomaly Detection Using Randomized Measurements and Variable Subsampling
Kölle, Michael
Ahouzi, Afrae
Debus, Pascal
Çetiner, Elif
Müller, Robert
Schuman, Daniëlle
Linnhoff-Popien, Claudia
Machine Learning
Artificial Intelligence
Quantum Physics
Quantum one-class support vector machines leverage the advantage of quantum kernel methods for semi-supervised anomaly detection. However, their quadratic time complexity with respect to data size poses challenges when dealing with large datasets. In recent work, quantum randomized measurements kernels and variable subsampling were proposed, as two independent methods to address this problem. The former achieves higher average precision, but suffers from variance, while the latter achieves linear complexity to data size and has lower variance. The current work focuses instead on combining these two methods, along with rotated feature bagging, to achieve linear time complexity both to data size and to number of features. Despite their instability, the resulting models exhibit considerably higher performance and faster training and testing times.
title Efficient Quantum One-Class Support Vector Machines for Anomaly Detection Using Randomized Measurements and Variable Subsampling
topic Machine Learning
Artificial Intelligence
Quantum Physics
url https://arxiv.org/abs/2407.20753