Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks

TL;DR

This paper introduces a Hierarchical Detection Network (HDN) that combines hierarchical matching and deep learning to significantly improve gravitational wave detection efficiency while maintaining high accuracy.

Contribution

The paper presents a novel HDN architecture trained with a unique loss function, demonstrating substantial efficiency gains over traditional matched filtering methods.

Findings

79% efficiency gain with two-layer HDN

Maintains 0.2% error rate at high efficiency

Multi-layer HDN further improves accuracy and efficiency

Abstract

Gravitational wave astronomy is a vibrant field that leverages both classic and modern data processing techniques for the understanding of the universe. Various approaches have been proposed for improving the efficiency of the detection scheme, with hierarchical matched filtering being an important strategy. Meanwhile, deep learning methods have recently demonstrated both consistency with matched filtering methods and remarkable statistical performance. In this work, we propose Hierarchical Detection Network (HDN), a novel approach to efficient detection that combines ideas from hierarchical matching and deep learning. The network is trained using a novel loss function, which encodes simultaneously the goals of statistical accuracy and efficiency. We discuss the source of complexity reduction of the proposed model, and describe a general recipe for initialization with each layer specializing in different regions. We demonstrate the performance of HDN with experiments using open LIGO data and synthetic injections, and observe with two-layer models a $79\%$ efficiency gain compared with matched filtering at an equal error rate of $0.2\%$. Furthermore, we show how training a three-layer HDN initialized using two-layer model can further boost both accuracy and efficiency, highlighting the power of multiple simple layers in efficient detection.