DeepAI AI Chat
Log In Sign Up

Sparse Recovery Beyond Compressed Sensing: Separable Nonlinear Inverse Problems

by   Brett Bernstein, et al.

Extracting information from nonlinear measurements is a fundamental challenge in data analysis. In this work, we consider separable inverse problems, where the data are modeled as a linear combination of functions that depend nonlinearly on certain parameters of interest. These parameters may represent neuronal activity in a human brain, frequencies of electromagnetic waves, fluorescent probes in a cell, or magnetic relaxation times of biological tissues. Separable nonlinear inverse problems can be reformulated as underdetermined sparse-recovery problems, and solved using convex programming. This approach has had empirical success in a variety of domains, from geophysics to medical imaging, but lacks a theoretical justification. In particular, compressed-sensing theory does not apply, because the measurement operators are deterministic and violate incoherence conditions such as the restricted-isometry property. Our main contribution is a theory for sparse recovery adapted to deterministic settings. We show that convex programming succeeds in recovering the parameters of interest, as long as their values are sufficiently distinct with respect to the correlation structure of the measurement operator. The theoretical results are illustrated through numerical experiments for two applications: heat-source localization and estimation of brain activity from electroencephalography data.


Compressed sensing for inverse problems and the sample complexity of the sparse Radon transform

Compressed sensing allows for the recovery of sparse signals from few me...

Nonlinear approximation spaces for inverse problems

This paper is concerned with the ubiquitous inverse problem of recoverin...

Complex Field-Trainable ISTA for Linear and Nonlinear Inverse Problems

Complex-field linear/nonlinear inverse problems are central issues in wi...

GAN-based Projector for Faster Recovery in Compressed Sensing with Convergence Guarantees

A Generative Adversarial Network (GAN) with generator G trained to model...

Semi-Random Sparse Recovery in Nearly-Linear Time

Sparse recovery is one of the most fundamental and well-studied inverse ...

Hierarchical sparse recovery from hierarchically structured measurements

A new class of measurement operators for structured compressed sensing p...

Bilinear Compressed Sensing under known Signs via Convex Programming

We consider the bilinear inverse problem of recovering two vectors, x∈R^...