Recovering Weak Signals with Normalizing Flows
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.
Related
- NFDiag: High-dimensional MCMC Convergence Diagnosis with Normalizing Flows
- Fast and Flow-rious: Gravitational Wave Background Bayesian Model Comparison using Normalizing Flows and Nested Sampling
- CausticFlow: An Efficient Machine Learning Framework Combining Neural Differential Equations and Normalizing Flows for Binary Microlensing Parameter Inference
- Hierarchical Population Inference with Normalizing Flows for Binary Black Holes
- CausticFlow: An Efficient Machine Learning Framework Combining Neural Differential Equations and Normalizing Flows for Binary Microlensing Parameter Inference
BibTeX
@misc{yatawatta2026recovering,
title = {{Recovering Weak Signals with Normalizing Flows}},
author = {Sarod Yatawatta},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06382},
eprint = {2609.06382},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06382},
}
RIS
TY - UNPB
TI - Recovering Weak Signals with Normalizing Flows
AU - Sarod Yatawatta
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2609.06382
UR - https://arxiv.org/abs/2609.06382
AB - 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.
ER -