Plug-in estimation in high-dimensional linear inverse problems: A rigorous analysis

Alyson K. Fletcher, Parthe Pandit, Sundeep Rangan, Subrata Sarkar, Philip Schniter

Research output: Contribution to journalConference article

Abstract

Estimating a vector x from noisy linear measurements Ax + w often requires use of prior knowledge or structural constraints on x for accurate reconstruction. Several recent works have considered combining linear least-squares estimation with a generic or “plug-in” denoiser function that can be designed in a modular manner based on the prior knowledge about x. While these methods have shown excellent performance, it has been difficult to obtain rigorous performance guarantees. This work considers plug-in denoising combined with the recently-developed Vector Approximate Message Passing (VAMP) algorithm, which is itself derived via Expectation Propagation techniques. It shown that the mean squared error of this “plug-and-play" VAMP can be exactly predicted for high-dimensional right-rotationally invariant random A and Lipschitz denoisers. The method is demonstrated on applications in image recovery and parametric bilinear estimation.

Original languageEnglish (US)
Pages (from-to)7440-7449
Number of pages10
JournalAdvances in Neural Information Processing Systems
Volume2018-December
StatePublished - Jan 1 2018
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: Dec 2 2018Dec 8 2018

Fingerprint

Inverse problems
Message passing
Recovery

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Plug-in estimation in high-dimensional linear inverse problems : A rigorous analysis. / Fletcher, Alyson K.; Pandit, Parthe; Rangan, Sundeep; Sarkar, Subrata; Schniter, Philip.

In: Advances in Neural Information Processing Systems, Vol. 2018-December, 01.01.2018, p. 7440-7449.

Research output: Contribution to journalConference article

Fletcher, Alyson K. ; Pandit, Parthe ; Rangan, Sundeep ; Sarkar, Subrata ; Schniter, Philip. / Plug-in estimation in high-dimensional linear inverse problems : A rigorous analysis. In: Advances in Neural Information Processing Systems. 2018 ; Vol. 2018-December. pp. 7440-7449.
@article{ab9adaed0c5f44c59beb5a5e73bca68c,
title = "Plug-in estimation in high-dimensional linear inverse problems: A rigorous analysis",
abstract = "Estimating a vector x from noisy linear measurements Ax + w often requires use of prior knowledge or structural constraints on x for accurate reconstruction. Several recent works have considered combining linear least-squares estimation with a generic or “plug-in” denoiser function that can be designed in a modular manner based on the prior knowledge about x. While these methods have shown excellent performance, it has been difficult to obtain rigorous performance guarantees. This work considers plug-in denoising combined with the recently-developed Vector Approximate Message Passing (VAMP) algorithm, which is itself derived via Expectation Propagation techniques. It shown that the mean squared error of this “plug-and-play{"} VAMP can be exactly predicted for high-dimensional right-rotationally invariant random A and Lipschitz denoisers. The method is demonstrated on applications in image recovery and parametric bilinear estimation.",
author = "Fletcher, {Alyson K.} and Parthe Pandit and Sundeep Rangan and Subrata Sarkar and Philip Schniter",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2018-December",
pages = "7440--7449",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Plug-in estimation in high-dimensional linear inverse problems

T2 - A rigorous analysis

AU - Fletcher, Alyson K.

AU - Pandit, Parthe

AU - Rangan, Sundeep

AU - Sarkar, Subrata

AU - Schniter, Philip

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Estimating a vector x from noisy linear measurements Ax + w often requires use of prior knowledge or structural constraints on x for accurate reconstruction. Several recent works have considered combining linear least-squares estimation with a generic or “plug-in” denoiser function that can be designed in a modular manner based on the prior knowledge about x. While these methods have shown excellent performance, it has been difficult to obtain rigorous performance guarantees. This work considers plug-in denoising combined with the recently-developed Vector Approximate Message Passing (VAMP) algorithm, which is itself derived via Expectation Propagation techniques. It shown that the mean squared error of this “plug-and-play" VAMP can be exactly predicted for high-dimensional right-rotationally invariant random A and Lipschitz denoisers. The method is demonstrated on applications in image recovery and parametric bilinear estimation.

AB - Estimating a vector x from noisy linear measurements Ax + w often requires use of prior knowledge or structural constraints on x for accurate reconstruction. Several recent works have considered combining linear least-squares estimation with a generic or “plug-in” denoiser function that can be designed in a modular manner based on the prior knowledge about x. While these methods have shown excellent performance, it has been difficult to obtain rigorous performance guarantees. This work considers plug-in denoising combined with the recently-developed Vector Approximate Message Passing (VAMP) algorithm, which is itself derived via Expectation Propagation techniques. It shown that the mean squared error of this “plug-and-play" VAMP can be exactly predicted for high-dimensional right-rotationally invariant random A and Lipschitz denoisers. The method is demonstrated on applications in image recovery and parametric bilinear estimation.

UR - http://www.scopus.com/inward/record.url?scp=85062725996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062725996&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85062725996

VL - 2018-December

SP - 7440

EP - 7449

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -