On the glassy nature of the hard phase in inference problems - Archive ouverte HAL Access content directly
Journal Articles Physical Review X Year : 2019

On the glassy nature of the hard phase in inference problems

(1, 2) , (3) , (1) , (1)
1
2
3

Abstract

An algorithmically hard phase was described in a range of inference problems: even if the signal can be reconstructed with a small error from an information theoretic point of view, known algorithms fail unless the noise-to-signal ratio is sufficiently small. This $hard\ phase$ is typically understood as a metastable branch of the dynamical evolution of message passing algorithms. In this work we study the metastable branch for a prototypical inference problem, the low-rank matrix factorization, that presents a hard phase. We show that for noise-to-signal ratios that are below the information theoretic threshold, the posterior measure is composed of an exponential number of metastable glassy states and we compute their entropy, called the complexity. We show that this glassiness extends even slightly below the algorithmic threshold below which the well-known approximate message passing (AMP) algorithm is able to closely reconstruct the signal. Counter-intuitively, we find that the performance of the AMP algorithm is not improved by taking into account the glassy nature of the hard phase.
Fichier principal
Vignette du fichier
glassynature.pdf (200.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

cea-01930645 , version 1 (22-11-2018)

Identifiers

Cite

Fabrizio Antenucci, Silvio Franz, Pierfrancesco Urbani, Lenka Zdeborová. On the glassy nature of the hard phase in inference problems. Physical Review X, 2019, 9, pp.011020. ⟨cea-01930645⟩
80 View
96 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More