Recovering Weak Signals with Normalizing Flows
TL;DR
This work proposes the use of normalizing flow models to reconstruct calibration-affected weak signals by leveraging the statistical invariance of the target signals and assuming minimal initial suppression, and effectively recovers the lost signal components.
Abstract
In many scientific disciplines, weak signals of interest are obscured by dominant nuisance signals that are several orders of magnitude stronger. Recovering these weak signals requires subtracting the dominant ones; however, this calibration process inherently distorts or partially suppresses the underlying signal of interest. To address this problem, we propose the use of normalizing flow models to reconstruct calibration-affected weak signals. By leveraging the statistical invariance of the target signals and assuming minimal initial suppression, our framework effectively recovers the lost signal components. We provide a comprehensive theoretical overview of this normalizing flow-based recovery method and demonstrate its efficacy using simulated data.
![Director of Machine Learning Insights [Part 4]](/uploads/articles/4d4046d553c83e57a3aa9af0665a2d2d482ad7c9.png)