Quantum-inspired tensor network autoencoders for anomaly detection: a MERA-based approach
- 1Sinop University
- 2Karlsruhe Institute of Technology (KIT)
- 3Karlsruhe Institute of Technology
Abstract
We investigate whether a multiscale tensor-network architecture provides a useful inductive bias for reconstruction-based anomaly detection in collider jets. Jets are produced by a branching cascade, so their internal structure is naturally organised across angular and momentum scales. This motivates an autoencoder that compresses information hierarchically and can reorganise short-range correlations before coarse-graining. Guided by this picture, we formulate a Multiscale Entanglement Renormalization Ansatz (MERA)-inspired autoencoder acting directly on ordered jet constituents. To our knowledge, a MERA-inspired autoencoder has not previously been proposed, and this architecture has not been explored in collider anomaly detection. We compare this architecture to a dense autoencoder, the corresponding tree-tensor-network limit, and standard classical baselines within a background-only reconstruction framework. The paper is organised around two main questions: whether locality-aware hierarchical compression is genuinely supported by the data, and whether the disentangling layers of MERA contribute beyond a simpler tree hierarchy. To address these questions, we combine benchmark comparisons with a training-free local-compressibility diagnostic and a direct identity-disentangler ablation. In the nominal benchmark, the MERA-inspired model attains a higher mean AUC than the dense autoencoder at all three latent dimensions while using roughly one-third of its trainable parameters. The locality-preserving multiscale structure is well matched to jet data, and, at the strongest compression bottleneck, the trained disentanglers move substantially away from the identity and are accompanied by a positive mean performance shift. Overall, the study supports locality-aware hierarchical compression as a useful and parameter-efficient inductive bias for reconstruction-based jet anomaly detection in this benchmark setting.
Related
- Anomaly detection in Fink. I. Discovery, follow-up, and classification of unusual sources
- PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
- Evaluating Zero-Shot Anomaly Detection for Identifying Unusual Galaxy Morphologies in CEERS and NGDEEP
- Comparing Active Anomaly Detection Frameworks: From Light Curves to Images
- MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO data
BibTeX
@article{gurkanli2026quantuminspired,
title = {{Quantum-inspired tensor network autoencoders for anomaly detection: a MERA-based approach}},
author = {Emre Gurkanli and Michael Spannowsky},
journal = {The European Physical Journal C},
year = {2026},
month = oct,
doi = {10.1140/epjc/s10052-026-16489-z},
url = {https://link.springer.com/article/10.1140/epjc/s10052-026-16489-z},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Quantum-inspired tensor network autoencoders for anomaly detection: a MERA-based approach
AU - Emre Gurkanli
AU - Michael Spannowsky
PY - 2026
DA - 2026/10/22
JO - The European Physical Journal C
DO - 10.1140/epjc/s10052-026-16489-z
UR - https://link.springer.com/article/10.1140/epjc/s10052-026-16489-z
AB - We investigate whether a multiscale tensor-network architecture provides a useful inductive bias for reconstruction-based anomaly detection in collider jets. Jets are produced by a branching cascade, so their internal structure is naturally organised across angular and momentum scales. This motivates an autoencoder that compresses information hierarchically and can reorganise short-range correlations before coarse-graining. Guided by this picture, we formulate a Multiscale Entanglement Renormalization Ansatz (MERA)-inspired autoencoder acting directly on ordered jet constituents. To our knowledge, a MERA-inspired autoencoder has not previously been proposed, and this architecture has not been explored in collider anomaly detection. We compare this architecture to a dense autoencoder, the corresponding tree-tensor-network limit, and standard classical baselines within a background-only reconstruction framework. The paper is organised around two main questions: whether locality-aware hierarchical compression is genuinely supported by the data, and whether the disentangling layers of MERA contribute beyond a simpler tree hierarchy. To address these questions, we combine benchmark comparisons with a training-free local-compressibility diagnostic and a direct identity-disentangler ablation. In the nominal benchmark, the MERA-inspired model attains a higher mean AUC than the dense autoencoder at all three latent dimensions while using roughly one-third of its trainable parameters. The locality-preserving multiscale structure is well matched to jet data, and, at the strongest compression bottleneck, the trained disentanglers move substantially away from the identity and are accompanied by a positive mean performance shift. Overall, the study supports locality-aware hierarchical compression as a useful and parameter-efficient inductive bias for reconstruction-based jet anomaly detection in this benchmark setting.
SN - 1434-6044
SN - 1434-6052
ER -