This is SPIRAL-TAP: Sparse Poisson Intensity Reconstruction ALgorithms - Theory and Practice

TL;DR

This paper introduces SPIRAL-TAP, a novel algorithm for reconstructing sparse Poisson intensities from count data, addressing challenges in inverse problems with nonnegative, high-dimensional unknowns.

Contribution

It develops a new optimization framework using penalized negative Poisson log-likelihood with quadratic approximations and sparsity-promoting penalties, advancing Poisson inverse problem solutions.

Findings

Effective reconstruction of sparse Poisson intensities demonstrated.

Incorporates quadratic approximation and sparsity penalties for improved accuracy.

Applicable to high-dimensional inverse problems with nonnegative constraints.

Abstract

The observations in many applications consist of counts of discrete events, such as photons hitting a detector, which cannot be effectively modeled using an additive bounded or Gaussian noise model, and instead require a Poisson noise model. As a result, accurate reconstruction of a spatially or temporally distributed phenomenon (f*) from Poisson data (y) cannot be effectively accomplished by minimizing a conventional penalized least-squares objective function. The problem addressed in this paper is the estimation of f* from y in an inverse problem setting, where (a) the number of unknowns may potentially be larger than the number of observations and (b) f* admits a sparse approximation. The optimization formulation considered in this paper uses a penalized negative Poisson log-likelihood objective function with nonnegativity constraints (since Poisson intensities are naturally nonnegative). In particular, the proposed approach incorporates key ideas of using separable quadratic approximations to the objective function at each iteration and penalization terms related to l1 norms of coefficient vectors, total variation seminorms, and partition-based multiscale estimation methods.