Details
| Original language | English |
|---|---|
| Article number | 022443 |
| Journal | Physical Review A |
| Volume | 110 |
| Issue number | 2 |
| Publication status | Published - 28 Aug 2024 |
Abstract
A normalizing flow computes a bijective mapping from an arbitrary distribution to a predefined (e.g., normal) distribution. Such a flow can be used to address different tasks, e.g., anomaly detection, once such a mapping has been learned. In this work we introduce normalizing flows for quantum architectures, describe how to model and optimize such a flow, and evaluate our method on example datasets. Our proposed models show competitive performance for anomaly detection compared to classical methods, especially those ones where there are already quantum inspired algorithms available. In the experiments we compare our performace to isolation forests (IF), the local outlier factor (LOF), or single-class SVMs.
ASJC Scopus subject areas
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Physical Review A, Vol. 110, No. 2, 022443, 28.08.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Quantum normalizing flows for anomaly detection
AU - Rosenhahn, Bodo
AU - Hirche, Christoph
N1 - Publisher Copyright: © 2024 American Physical Society.
PY - 2024/8/28
Y1 - 2024/8/28
N2 - A normalizing flow computes a bijective mapping from an arbitrary distribution to a predefined (e.g., normal) distribution. Such a flow can be used to address different tasks, e.g., anomaly detection, once such a mapping has been learned. In this work we introduce normalizing flows for quantum architectures, describe how to model and optimize such a flow, and evaluate our method on example datasets. Our proposed models show competitive performance for anomaly detection compared to classical methods, especially those ones where there are already quantum inspired algorithms available. In the experiments we compare our performace to isolation forests (IF), the local outlier factor (LOF), or single-class SVMs.
AB - A normalizing flow computes a bijective mapping from an arbitrary distribution to a predefined (e.g., normal) distribution. Such a flow can be used to address different tasks, e.g., anomaly detection, once such a mapping has been learned. In this work we introduce normalizing flows for quantum architectures, describe how to model and optimize such a flow, and evaluate our method on example datasets. Our proposed models show competitive performance for anomaly detection compared to classical methods, especially those ones where there are already quantum inspired algorithms available. In the experiments we compare our performace to isolation forests (IF), the local outlier factor (LOF), or single-class SVMs.
UR - http://www.scopus.com/inward/record.url?scp=85203588645&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2402.02866
DO - 10.48550/arXiv.2402.02866
M3 - Article
AN - SCOPUS:85203588645
VL - 110
JO - Physical Review A
JF - Physical Review A
SN - 2469-9926
IS - 2
M1 - 022443
ER -