Enhancing anomaly detection with topology-aware autoencoders

TL;DR

This paper introduces topology-aware autoencoders with manifold-embedded latent spaces to improve anomaly detection in high-energy physics, demonstrating enhanced sensitivity and robustness over traditional Euclidean autoencoders.

Contribution

It proposes novel autoencoder architectures with topologically constrained latent spaces, reflecting physical conservation laws, and shows their superior performance in anomaly detection tasks.

Findings

Topology-aware autoencoders outperform Euclidean ones in anomaly separation.

Latent spaces with topological priors improve sensitivity to anomalous events.

Topological constraints reduce spurious reconstruction errors.

Abstract

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.