Identifying and Mitigating Machine Learning Biases for the Gravitational Wave Detection Problem

Abstract

Matched filtering is a long-standing technique for the optimal detection of known signals in stationary Gaussian noise. However, it has known departures from optimality when operating on unknown signals in real noise and suffers from computational inefficiencies in its pursuit of near-optimality. A compelling alternative that has emerged in recent years to address this problem is deep learning. Although it has shown significant promise when applied to the search for gravitational waves (GWs) in detector noise, we demonstrate the existence of learning biases that hinder generalisation and lead to significant loss in detection sensitivity. Our work identifies the sources of a set of 11 interconnected biases present in the supervised learning of the GW detection problem and contributes mitigation tactics and training strategies to concurrently address them. In light of the identified biases, we demonstrate that existing detection sensitivity metrics are not reliable for machine-learning (ML) pipelines and discuss the trustworthiness of previous results. We use GW domain knowledge to build a bespoke ML based binary black hole search pipeline called Sage that addresses these biases. Via the injection study presented in the Machine Learning Gravitational-Wave Search Challenge, we show that Sage detects ~11.2% more signals than the benchmark PyCBC analysis at a false alarm rate of one per month in O3a noise. Moreover, we also show that it can detect ~48.29% more signals than the previous best-performing ML pipeline on the same dataset. We empirically prove that Sage can: [i] effectively handle out-of-distribution noise power spectral densities, [ii] strongly reject non-Gaussian transient noise artefacts, and [iii] achieve higher detection sensitivities using less data than network architectures of a similar size. All code and implementations are available at https://github.com/nnarenraju/sage.

41 pages (34 pages main text), 24 figures

References in corpus (22)

• Advanced LIGO
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run
• Computationally efficient models for the dominant and sub-dominant harmonic modes of precessing binary black holes
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• 4-OGC: Catalog of gravitational waves from compact-binary mergers
• A template bank to search for gravitational waves from inspiralling compact binaries I: physical models
• Gravitational waves from inspiralling compact binaries: hexagonal template placement and its efficiency in detecting physical signals
• Omicron: a tool to characterize transient noise in gravitational-wave detectors
• The Emergence of Structure in the Binary Black Hole Mass Distribution
• Measuring gravitational-wave higher-order modes
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Quantifying the Effect of Power Spectral Density Uncertainty on Gravitational-Wave Parameter Estimation for Compact Binary Sources
• Deep Residual Networks for Gravitational Wave Detection
• Identifying when Precession can be Measured in Gravitational Waveforms
• From One to Many: A Deep Learning Coincident Gravitational-Wave Search
• Generalized Approach to Matched Filtering using Neural Networks
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Adapting to noise distribution shifts in flow-based gravitational-wave inference
• Optimized Search for a Binary Black Hole Merger Population in LIGO-Virgo O3 Data
• Data analysis of continuous gravitational wave: All sky search and study of templates

Cited by in corpus (1)

• Transformer Networks for Continuous Gravitational-wave Searches