Weighted conformal prediction improves detection of gravitational waves
Improving the Sensitivity of Gravitational Wave Detection with Weighted Conformal Prediction
Machine Learning
Summary
Gravitational wave detectors pick up signals from space, but the data is very noisy, making it hard to find real events. The authors use a method that combines results from several detection algorithms and gives reliable confidence levels for candidate signals. They improve this method to handle differences between simulated training data and real observations, which helps avoid mistakes in estimating signal confidence. Their approach recovers real signals that might otherwise be missed, making detections more sensitive and reliable.
What this means in practice
- •For gravitational wave data analysts: Provide more accurate confidence levels for candidate gravitational wave events by combining multiple pipelines while adjusting for changes between training simulations and real data.
- •For signal processing engineers: Enhance detection sensitivity in noisy environments by integrating weighted conformal prediction methods that correct for data distribution changes over time.
Authors
Ann-Kristin Malz, Gregory Ashton, Nicolo Colombo
Abstract
In the last decade, kilometre-scale interferometric gravitational-wave detectors have observed hundreds of compact binary mergers, the majority of which are binary black holes. However, the data are noise-dominated, and multiple independent search algorithms (pipelines) are used to enhance sensitivity and improve robustness. Rather than the standard approach of selecting the most significant pipeline output, we combine the outputs from all pipelines using a conformal prediction-based framework to provide statistically rigorous confidence estimates for candidate events. While combining pipelines improves sensitivity and ranking robustness, it requires a principled statistical framework that remains valid as data properties evolve across observing runs. A key challenge is distribution shifts between simulated datasets used for training and calibration and the real, unlabelled, observations used for testing, which can invalidate coverage guarantees and bias confidence estimates. In this work, we address this challenge by incorporating likelihood-ratio reweighting into our conformal prediction framework to account for covariate shift. Using mock datasets containing simulated signals, we demonstrate that weighted conformal prediction restores well-calibrated coverage under covariate shift and increases the confidence of events near the detection threshold, recovering true signals that would otherwise be missed.