On the universality of noiseless linear estimation with respect to the measurement matrix - Archive ouverte HAL Access content directly
Journal Articles Journal of Physics A: Mathematical and Theoretical Year : 2020

On the universality of noiseless linear estimation with respect to the measurement matrix

(1) , (1) , (1) , (2)
1
2

Abstract

In a noiseless linear estimation problem, one aims to reconstruct a vector x * from the knowledge of its linear projections y = Φx *. There have been many theoretical works concentrating on the case where the matrix Φ is a random i.i.d. one, but a number of heuristic evidence suggests that many of these results are universal and extend well beyond this restricted case. Here we revisit this problematic through the prism of development of message passing methods, and consider not only the universality of the 1 transition, as previously addressed, but also the one of the optimal Bayesian reconstruction. We observed that the universality extends to the Bayes-optimal minimum mean-squared (MMSE) error, and to a range of structured matrices.
Fichier principal
Vignette du fichier
1906.04735.pdf (550.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

cea-02528193 , version 1 (01-04-2020)

Identifiers

Cite

Alia Abbara, Antoine Baker, Florent Krzakala, Lenka Zdeborová. On the universality of noiseless linear estimation with respect to the measurement matrix. Journal of Physics A: Mathematical and Theoretical, 2020, 53 (16), pp.164001. ⟨10.1088/1751-8121/ab59ef⟩. ⟨cea-02528193⟩
60 View
45 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More