Transformer Networks for Continuous Gravitational-wave Searches

Abstract

Wide-parameter-space searches for continuous gravitational waves using semi-coherent matched-filter methods require enormous computing power, which limits their achievable sensitivity. Here we explore an alternative search method based on training neural networks as classifiers on detector strain data with minimal pre-processing. Contrary to previous studies using convolutional neural networks (CNNs), we investigate the suitability of the transformer architecture, specifically the Vision Transformer (ViT). We establish sensitivity benchmarks using the matched-filter $\mathcal{F}$-statistic for ten targeted searches over a ten day timespan, and ten directed and six all-sky searches over a one day timespan. We train ViTs on each of these benchmark cases. The trained ViTs achieve essentially matched-filter sensitivity on the targeted benchmarks, and approach the $\mathcal{F}$-statistic detection probability of $p_{\det }$ = 90% on the directed ($p_{\det }\approx$ 85-89 %) and all-sky benchmarks ($p_{\det }\approx$ 78-88 %). Unlike the CNNs in our previous studies, which required extensive manual design and hyperparameter tuning, the ViT achieves better performance with a standard architecture and minimal tuning.

10 pages, 4 figures, 4 tables

References in corpus (24)

• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• Data analysis of gravitational-wave signals from spinning neutron stars. I. The signal and its detection
• Searches for Continuous-Wave Gravitational Radiation
• Deep-Learning continuous gravitational waves
• Fast and Accurate Sensitivity Estimation for Continuous-Gravitational-Wave Searches
• Searches for continuous gravitational waves from neutron stars: A twenty-year retrospective
• How effective is machine learning to detect long transient gravitational waves from neutron stars in a real search?
• Estimating the sensitivity of wide-parameter-space searches for gravitational-wave pulsars
• Deep learning for clustering of continuous gravitational wave candidates
• Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
• Training Strategies for Deep Learning Gravitational-Wave Searches
• Implementing a semicoherent search for continuous gravitational waves using optimally-constructed template banks
• SOAP: A generalised application of the Viterbi algorithm to searches for continuous gravitational-wave signals
• A robust machine learning algorithm to search for continuous gravitational waves
• Deep learning for clustering of continuous gravitational wave candidates II: identification of low-SNR candidates
• Rapid parameter estimation for an all-sky continuous gravitational wave search using conditional varitational auto-encoders
• Use of Excess Power Method and Convolutional Neural Network in All-Sky Search for Continuous Gravitational Waves
• Convolutional neural network search for long-duration transient gravitational waves from glitching pulsars
• Assessing the impact of non-Gaussian noise on convolutional neural networks that search for continuous gravitational waves
• Novel neural-network architecture for continuous gravitational waves
• Large-kernel Convolutional Neural Networks for Wide Parameter-Space Searches of Continuous Gravitational Waves
• Identifying and Mitigating Machine Learning Biases for the Gravitational Wave Detection Problem
• Learning to detect continuous gravitational waves: an open data-analysis competition

Cited by in corpus (1)

• Flexible Gravitational-Wave Parameter Estimation with Transformers