2016
DOI: 10.1103/physreve.94.022137
|View full text |Cite
|
Sign up to set email alerts
|

Bayesian online compressed sensing

Abstract: In this paper, we explore the possibilities and limitations of recovering sparse signals in an online fashion. Employing a mean field approximation to the Bayes recursion formula yields an online signal recovery algorithm that can be performed with a computational cost that is linearly proportional to the signal length per update. Analysis of the resulting algorithm indicates that the online algorithm asymptotically saturates the optimal performance limit achieved by the offline method in the presence of Gauss… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

2
25
0

Year Published

2017
2017
2020
2020

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(27 citation statements)
references
References 32 publications
2
25
0
Order By: Relevance
“…It has been shown [24] that this online algorithm has an asymptotic error decay comparable to the offline reconstruction scheme when additive measurement noise is present. In the noiseless scenario, the offline Bayesian algorithm achieves zero error for finite t, while the online version decays exponentially.…”
Section: Bayesian Online Compressed Sensingmentioning
confidence: 99%
See 4 more Smart Citations
“…It has been shown [24] that this online algorithm has an asymptotic error decay comparable to the offline reconstruction scheme when additive measurement noise is present. In the noiseless scenario, the offline Bayesian algorithm achieves zero error for finite t, while the online version decays exponentially.…”
Section: Bayesian Online Compressed Sensingmentioning
confidence: 99%
“…The δ(x) factor here adds a singularity to the prior φ(x), so that the posterior should not approximate a Gaussian distribution even for t → ∞, which was a crucial hypothesis in previous works [16] and would greatly simplify asymptotic calculations. In absence of such a simplification, a previous work [24] introduced the following mean-field approximation:…”
Section: Bayesian Online Compressed Sensingmentioning
confidence: 99%
See 3 more Smart Citations