Compressed Sensing using Generative Models

03/09/2017
by   Ashish Bora, et al.
0

The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model G: R^k →R^n. Our main theorem is that, if G is L-Lipschitz, then roughly O(k L) random Gaussian measurements suffice for an ℓ_2/ℓ_2 recovery guarantee. We demonstrate our results using generative models from published variational autoencoder and generative adversarial networks. Our method can use 5-10x fewer measurements than Lasso for the same accuracy.

READ FULL TEXT

page 8

page 9

page 20

page 22

page 23

page 24

research
12/06/2019

Lower Bounds for Compressed Sensing with Generative Models

The goal of compressed sensing is to learn a structured signal x from a ...
research
07/04/2018

Modeling Sparse Deviations for Compressed Sensing using Generative Models

In compressed sensing, a small number of linear measurements can be used...
research
06/17/2018

Compressed Sensing with Deep Image Prior and Learned Regularization

We propose a novel method for compressed sensing recovery using untraine...
research
12/19/2018

Derandomizing compressed sensing with combinatorial design

Compressed sensing is the art of reconstructing structured n-dimensional...
research
06/26/2018

The Sparse Recovery Autoencoder

Linear encoding of sparse vectors is widely popular, but is most commonl...
research
04/26/2022

Decoding noisy messages: a method that just shouldn't work

This paper is about receiving text messages through a noisy and costly l...
research
06/28/2022

Equivariant Priors for Compressed Sensing with Unknown Orientation

In compressed sensing, the goal is to reconstruct the signal from an und...

Please sign up or login with your details

Forgot password? Click here to reset