Robust one-bit compressed sensing with non-Gaussian measurements

by   Sjoerd Dirksen, et al.

We study memoryless one-bit compressed sensing with non-Gaussian measurement matrices. We show that by quantizing at uniformly distributed thresholds, it is possible to accurately reconstruct low-complexity signals from a small number of one-bit quantized measurements, even if the measurement vectors are drawn from a heavy-tailed distribution. Our reconstruction results are uniform in nature and robust in the presence of pre-quantization noise on the analog measurements as well as adversarial bit corruptions in the quantization process. If the measurement matrix is subgaussian, then accurate recovery can be achieved via a convex program. Our reconstruction theorems rely on a new random hyperplane tessellation result, which is of independent interest.


page 1

page 2

page 3

page 4


Robust one-bit compressed sensing with partial circulant matrices

We present optimal sample complexity estimates for one-bit compressed se...

Quantized Compressed Sensing by Rectified Linear Units

This work is concerned with the problem of recovering high-dimensional s...

Dictionary-Sparse Recovery From Heavy-Tailed Measurements

The recovery of signals that are sparse not in a basis, but rather spars...

Beyond Independent Measurements: General Compressed Sensing with GNN Application

We consider the problem of recovering a structured signal 𝐱∈ℝ^n from noi...

Robust compressed sensing of generative models

The goal of compressed sensing is to estimate a high dimensional vector ...

Robust One-Bit Recovery via ReLU Generative Networks: Improved Statistical Rates and Global Landscape Analysis

We study the robust one-bit compressed sensing problem whose goal is to ...

Please sign up or login with your details

Forgot password? Click here to reset