Enhancing anomaly detection with topology-aware autoencoders
This work addresses the need for better unsupervised anomaly detection in particle physics to identify new physics beyond the Standard Model, representing an incremental improvement over existing autoencoder methods.
The paper tackled the problem of anomaly detection in high-energy physics by developing topology-aware autoencoders with latent spaces like spherical and projective manifolds, which improved anomaly separation by preserving data structure and reducing errors, as demonstrated in simulated top-quark decay data.
Anomaly detection in high-energy physics is essential for identifying new physics beyond the Standard Model. Autoencoders provide a signal-agnostic approach but are limited by the topology of their latent space. This work explores topology-aware autoencoders, embedding phase-space distributions onto compact manifolds that reflect energy-momentum conservation. We construct autoencoders with spherical ($S^n$), product ($S^2 \otimes S^2$), and projective ($\mathbb{RP}^2$) latent spaces and compare their anomaly detection performance against conventional Euclidean embeddings. Our results show that autoencoders with topological priors significantly improve anomaly separation by preserving the global structure of the data manifold and reducing spurious reconstruction errors. Applying our approach to simulated hadronic top-quark decays, we show that latent spaces with appropriate topological constraints enhance sensitivity and robustness in detecting anomalous events. This study establishes topology-aware autoencoders as a powerful tool for unsupervised searches for new physics in particle-collision data.