Compressed Sensing using Generative Models

arXiv1703.03208MaRDI QIDQ6284108FDOQ6284108

Authors: Ashish Bora, Ajil Jalal, Eric Price, Alexandros G. Dimakis 

Publication date: 9 March 2017

Abstract: 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 $G:mathbb{R}^{k}omathbb{R}^n$. Our main theorem is that, if $G$ is $L$-Lipschitz, then roughly $O(klogL)$ random Gaussian measurements suffice for an $el{l}_2/el{l}_2$ recovery guarantee. We demonstrate our results using generative models from published variational autoencoder and generative adversarial networks. Our method can use $5$-$10$x fewer measurements than Lasso for the same accuracy.

Has companion code repository: https://github.com/gabsens/Compressed-Sensing-ENSAE

This page was built for publication: Compressed Sensing using Generative Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6284108)