Avoiding subtraction and division of stochastic signals using normalizing flows: NFdeconvolve

TL;DR

This paper introduces NFdeconvolve, a normalizing flow-based method that estimates the distribution of a stochastic signal component without performing subtraction or division, thereby reducing noise amplification in signal processing.

Contribution

The authors develop a novel approach using normalizing flows to recover stochastic signal statistics without subtraction or division, improving robustness against noise.

Findings

Successfully estimates signal distributions without subtraction/division

Reduces noise amplification in stochastic signal processing

Provides open-source software with tutorial for practical use

Abstract

Across the scientific realm, we find ourselves subtracting or dividing stochastic signals. For instance, consider a stochastic realization, $x$, generated from the addition or multiplication of two stochastic signals $a$ and $b$, namely $x=a+b$ or $x = ab$. For the $x=a+b$ example, $a$ can be fluorescence background and $b$ the signal of interest whose statistics are to be learned from the measured $x$. Similarly, when writing $x=ab$, $a$ can be thought of as the illumination intensity and $b$ the density of fluorescent molecules of interest. Yet dividing or subtracting stochastic signals amplifies noise, and we ask instead whether, using the statistics of $a$ and the measurement of $x$ as input, we can recover the statistics of $b$. Here, we show how normalizing flows can generate an approximation of the probability distribution over $b$, thereby avoiding subtraction or division altogether. This method is implemented in our software package, NFdeconvolve, available on GitHub with a tutorial linked in the main text.