It's not a FAD: first results in using Flows for unsupervised Anomaly Detection at 40 MHz at the Large Hadron Collider

TL;DR

This paper introduces a hardware-efficient Continuous Normalizing Flow model for real-time unsupervised anomaly detection at the Large Hadron Collider, capable of identifying new physics signatures within strict latency constraints.

Contribution

It presents the first FPGA-implementable CNF-based anomaly detection method with a novel, hardware-friendly scoring mechanism suitable for high-rate collider environments.

Findings

Effective detection of BSM signatures comparable to existing ML triggers

Achieves latency of a few hundred nanoseconds with minimal FPGA resources

Demonstrates feasibility of CNFs for real-time collider data analysis

Abstract

We present the first implementation of a Continuous Normalizing Flow (CNF) model for unsupervised anomaly detection within the realistic, high-rate environment of the Large Hadron Collider's L1 trigger systems. While CNFs typically define an anomaly score via a probabilistic likelihood, calculating this score requires solving an Ordinary Differential Equation, a procedure too complex for FPGA deployment. To overcome this, we propose a novel, hardware-friendly anomaly score defined as the squared norm of the model's vector field output. This score is based on the intuition that anomalous events require a larger transformation by the flow. Our model, trained via Flow Matching on Standard Model data, is synthesized for an FPGA using the hls4ml and da4ml libraries. We demonstrate that our approach effectively identifies a variety of beyond-the-Standard-Model signatures with performance comparable to existing machine learning-based triggers. The algorithm achieves a latency of a few hundred nanoseconds, or even less when using advanced quantization techniques, and requires minimal FPGA resources, establishing CNFs as a viable new tool for real-time, data-driven discovery at 40 MHz.