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 journalArticlepeer-review

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 recentlydeveloped 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)
Article number124021
JournalJournal of Statistical Mechanics: Theory and Experiment
Volume2019
Issue number12
DOIs
StatePublished - Dec 20 2019

Keywords

  • machine learning

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint Dive into the research topics of 'Plug in estimation in high dimensional linear inverse problems a rigorous analysis'. Together they form a unique fingerprint.

Cite this