Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
复制标题
DOI：
10.1103/physrevd.106.063008
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Jingkai Yan;R. Colgan;John N. Wright;Z. M'arka;I. Bartos;S. M'arka
中科院分区：
文献类型：
--
作者：
Jingkai Yan;R. Colgan;John N. Wright;Z. M'arka;I. Bartos;S. M'arka
引力波天文学是一个充满活力的领域，它利用经典和现代数据处理技术来理解宇宙。已经提出了各种方法来提高检测方案的效率，其中分层匹配滤波是一种重要的策略。同时，深度学习方法最近表现出与匹配滤波方法的一致性和显著的统计性能。在这项工作中，我们提出了层次检测网络(HDN)，这是一种结合了层次匹配和深度学习思想的有效检测方法。网络的训练使用了一种新的损失函数，该函数同时编码了统计精度和效率的目标。我们讨论了提出的模型降低复杂性的来源，并描述了初始化的一般方法，每一层专门针对不同的区域。我们用开放的LIGO数据和合成注入的实验验证了HDN的性能，并用两层模型观察到在相同误码率为0.2美元的情况下，与匹配滤波相比效率提高了79美元。此外，我们展示了如何训练一个用两层模型初始化的三层HDN，进一步提高了准确率和效率，突出了多个简单层在有效检测方面的力量。
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.