Learning-based Compressive Subsampling

by   Luca Baldassarre, et al.

The problem of recovering a structured signal x∈C^p from a set of dimensionality-reduced linear measurements b = Ax arises in a variety of applications, such as medical imaging, spectroscopy, Fourier optics, and computerized tomography. Due to computational and storage complexity or physical constraints imposed by the problem, the measurement matrix A∈C^n × p is often of the form A = P_ΩΨ for some orthonormal basis matrix Ψ∈C^p × p and subsampling operator P_Ω: C^p→C^n that selects the rows indexed by Ω. This raises the fundamental question of how best to choose the index set Ω in order to optimize the recovery performance. Previous approaches to addressing this question rely on non-uniform random subsampling using application-specific knowledge of the structure of x. In this paper, we instead take a principled learning-based approach in which a fixed index set is chosen based on a set of training signals x_1,,x_m. We formulate combinatorial optimization problems seeking to maximize the energy captured in these signals in an average-case or worst-case sense, and we show that these can be efficiently solved either exactly or approximately via the identification of modularity and submodularity structures. We provide both deterministic and statistical theoretical guarantees showing how the resulting measurement matrices perform on signals differing from the training signals, and we provide numerical examples showing our approach to be effective on a variety of data sets.


page 8

page 9

page 11

page 13


Compressive Phase Retrieval of Structured Signal

Compressive phase retrieval is the problem of recovering a structured ve...

Recovery under Side Constraints

This paper addresses sparse signal reconstruction under various types of...

A Unified Recovery of Structured Signals Using Atomic Norm

In many applications we seek to recover signals from linear measurements...

Probabilistic index maps for modeling natural signals

One of the major problems in modeling natural signals is that signals wi...

Signal Recovery with Non-Expansive Generative Network Priors

We study compressive sensing with a deep generative network prior. Initi...

RL-NCS: Reinforcement learning based data-driven approach for nonuniform compressed sensing

A reinforcement-learning-based non-uniform compressed sensing (NCS) fram...

Learning a Compressive Sensing Matrix with Structural Constraints via Maximum Mean Discrepancy Optimization

We introduce a learning-based algorithm to obtain a measurement matrix f...

Please sign up or login with your details

Forgot password? Click here to reset