A Unified Approach to Uniform Signal Recovery From Non-Linear Observations

09/19/2020
by   Martin Genzel, et al.
0

Recent advances in quantized compressed sensing and high-dimensional estimation have shown that signal recovery is even feasible under strong non-linear distortions in the observation process. An important characteristic of associated guarantees is uniformity, i.e., recovery succeeds for an entire class of structured signals with a fixed measurement ensemble. However, despite significant results in various special cases, a general understanding of uniform recovery from non-linear observations is still missing. This paper develops a unified approach to this problem under the assumption i.i.d. sub-Gaussian measurement vectors. Our main result shows that a simple least-squares estimator with any convex constraint can serve as a universal recovery strategy, which is outlier robust and does not require explicit knowledge of the underlying non-linearity. Based on empirical process theory, a key technical novelty is an approximative increment condition that can be implemented for all common types of non-linear models. This flexibility allows us to apply our approach to a variety of problems in quantized compressed sensing and high-dimensional statistics, leading to several new and improved guarantees. Each of these applications is accompanied by a conceptually simple and systematic proof, which does not rely on any deeper properties of the observation model. On the other hand, known local stability properties can be incorporated into our framework in a plug-and-play manner, thereby implying near-optimal error bounds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2021

Support Recovery in Universal One-bit Compressed Sensing

One-bit compressed sensing (1bCS) is an extreme-quantized signal acquisi...
research
10/29/2022

Improved Support Recovery in Universal One-bit Compressed Sensing

One-bit compressed sensing (1bCS) is an extremely quantized signal acqui...
research
03/24/2021

Quantized Corrupted Sensing with Random Dithering

Corrupted sensing concerns the problem of recovering a high-dimensional ...
research
09/11/2019

Goodness-of-fit tests on manifolds

We develop a general theory for the goodness-of-fit test to non-linear m...
research
04/13/2018

Robust 1-Bit Compressed Sensing via Hinge Loss Minimization

This work theoretically studies the problem of estimating a structured h...
research
12/30/2022

Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery

This paper studies the quantization of heavy-tailed data in some fundame...
research
02/24/2016

A Compressed Sensing Based Decomposition of Electrodermal Activity Signals

The measurement and analysis of Electrodermal Activity (EDA) offers appl...

Please sign up or login with your details

Forgot password? Click here to reset