Minimax Optimal Rates for Poisson Inverse Problems With Physical Constraints

DOI10.1109/TIT.2015.2441072zbMATH Open1359.94106arXiv1403.6532OpenAlexW2404602641WikidataQ98839713 ScholiaQ98839713MaRDI QIDQ2977355FDOQ2977355

Authors: Xin Jiang, Garvesh Raskutti, Rebecca Willett 

Publication date: 28 April 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: This paper considers fundamental limits for solving sparse inverse problems in the presence of Poisson noise with physical constraints. Such problems arise in a variety of applications, including photon-limited imaging systems based on compressed sensing. Most prior theoretical results in compressed sensing and related inverse problems apply to idealized settings where the noise is i.i.d., and do not account for signal-dependent noise and physical sensing constraints. Prior results on Poisson compressed sensing with signal-dependent noise and physical constraints provided upper bounds on mean squared error performance for a specific class of estimators. However, it was unknown whether those bounds were tight or if other estimators could achieve significantly better performance. This work provides minimax lower bounds on mean-squared error for sparse Poisson inverse problems under physical constraints. Our lower bounds are complemented by minimax upper bounds. Our upper and lower bounds reveal that due to the interplay between the Poisson noise model, the sparsity constraint and the physical constraints: (i) the mean-squared error does not depend on the sample size $n$ other than to ensure the sensing matrix satisfies RIP-like conditions and the intensity $T$ of the input signal plays a critical role; and (ii) the mean-squared error has two distinct regimes, a low-intensity and a high-intensity regime and the transition point from the low-intensity to high-intensity regime depends on the input signal $f^{*}$. In the low-intensity regime the mean-squared error is independent of $T$ while in the high-intensity regime, the mean-squared error scales as $fracslogpT$, where $s$ is the sparsity level, $p$ is the number of pixels or parameters and $T$ is the signal intensity.

Full work available at URL: https://arxiv.org/abs/1403.6532

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Information theory (general) (94A15)

Cited In (8)

• High dimensional generalized linear models for temporal dependent data
• Super-resolution of positive sources: the discrete setup
• Learning Markov models via low-rank optimization
• An optimal statistical and computational framework for generalized tensor estimation
• Sparse space-time models: concentration inequalities and Lasso
• Compound Poisson point processes, concentration and oracle inequalities
• Variance-stabilization-based compressive inversion under Poisson or Poisson–Gaussian noise with analytical bounds
• Cross: efficient low-rank tensor completion

This page was built for publication: Minimax Optimal Rates for Poisson Inverse Problems With Physical Constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2977355)