Identifying and Mitigating Machine Learning Biases for the Gravitational Wave Detection Problem
arXiv:2501.13846 · doi:10.1103/zwj9-ycyz
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 (48)
- Overcoming catastrophic forgetting in neural networks
- GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
- Advanced LIGO
- Res2Net: A New Multi-scale Backbone Architecture
- 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
- GW150914: The Advanced LIGO Detectors in the Era of First Discoveries
- The PyCBC search for gravitational waves from compact binary coalescence
- FINDCHIRP: an algorithm for detection of gravitational waves from inspiraling compact binaries
- Computationally efficient models for the dominant and sub-dominant harmonic modes of precessing binary black holes
- GW150914: First results from the search for binary black hole coalescence with Advanced LIGO
- The Sensitivity of the Advanced LIGO Detectors at the Beginning of Gravitational Wave Astronomy
- Matched filtering of gravitational waves from inspiraling compact binaries: Computational cost and template placement
- Analysis Framework for the Prompt Discovery of Compact Binary Mergers in Gravitational-wave Data
- Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
- A guide to LIGO-Virgo detector noise and extraction of transient gravitational-wave signals
- Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
- A chi-squared time-frequency discriminator for gravitational wave detection
- Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914
- Event rate estimates for LISA extreme mass ratio capture sources
- Matching matched filtering with deep networks in gravitational-wave astronomy
- 4-OGC: Catalog of gravitational waves from compact-binary mergers
- Detecting binary compact-object mergers with gravitational waves: Understanding and Improving the sensitivity of the PyCBC search
- PyCBC Live: Rapid Detection of Gravitational Waves from Compact Binary Mergers
- Convolutional neural networks: a magic bullet for gravitational-wave detection?
- Effects of Data Quality Vetoes on a Search for Compact Binary Coalescences in Advanced LIGO's First Observing Run
- Blip glitches in Advanced LIGO data
- 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
- Distinguishing short duration noise transients in LIGO data to improve the PyCBC search for gravitational waves from high mass binary black hole mergers
- The Emergence of Structure in the Binary Black Hole Mass Distribution
- Measuring gravitational-wave higher-order modes
- Improving the Data Quality of Advanced LIGO Based on Early Engineering Run Results
- 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
- On the background estimation by time slides in a network of gravitational wave detectors
- Quantifying the Effect of Power Spectral Density Uncertainty on Gravitational-Wave Parameter Estimation for Compact Binary Sources
- Identifying when Precession can be Measured in Gravitational Waveforms
- Deep Residual Networks for Gravitational Wave Detection
- From One to Many: A Deep Learning Coincident Gravitational-Wave Search
- Generalized Approach to Matched Filtering using Neural Networks
- Optimizing gravitational-wave searches for a population of coalescing binaries: Intrinsic parameters
- 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
- Random template placement and prior information