Instance-Optimal Compressed Sensing via Posterior Sampling

06/21/2021
by   Ajil Jalal, et al.
6

We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors). We show for Gaussian measurements and any prior distribution on the signal, that the posterior sampling estimator achieves near-optimal recovery guarantees. Moreover, this result is robust to model mismatch, as long as the distribution estimate (e.g., from an invertible generative model) is close to the true distribution in Wasserstein distance. We implement the posterior sampling estimator for deep generative priors using Langevin dynamics, and empirically find that it produces accurate estimates with more diversity than MAP.

READ FULL TEXT

page 2

page 3

page 8

page 9

research
08/03/2021

Robust Compressed Sensing MRI with Deep Generative Priors

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep gen...
research
02/25/2021

Provable Compressed Sensing with Generative Priors via Langevin Dynamics

Deep generative models have emerged as a powerful class of priors for si...
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
09/01/2015

Sequential Information Guided Sensing

We study the value of information in sequential compressed sensing by ch...
research
11/02/2022

Quantized Compressed Sensing with Score-Based Generative Models

We consider the general problem of recovering a high-dimensional signal ...
research
01/03/2018

Theoretical links between universal and Bayesian compressed sensing algorithms

Quantized maximum a posteriori (Q-MAP) is a recently-proposed Bayesian c...
research
05/31/2022

Non-Iterative Recovery from Nonlinear Observations using Generative Models

In this paper, we aim to estimate the direction of an underlying signal ...

Please sign up or login with your details

Forgot password? Click here to reset