2021
DOI: 10.48550/arxiv.2107.11689
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

An inference problem in a mismatched setting: a spin-glass model with Mattis interaction

Francesco Camilli,
Pierluigi Contucci,
Emanuele Mingione

Abstract: The Wigner spiked model in a mismatched setting is studied with the finite temperature Statistical Mechanics approach through its representation as a Sherrington-Kirkpatrick model with added Mattis interaction. The exact solution of the model with Ising spins is rigorously proved to be given by a variational principle on two order parameters, the Parisi overlap distribution and the Mattis magnetization. The latter is identified by an ordinary variational principle and turns out to concentrate in the thermodyna… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
1
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 41 publications
0
1
0
Order By: Relevance
“…When instead the receiver ignores the prior or the signal-to-noise ratio, only a few results are available [20][21][22][23][24]. In such settings, called mismatched, the Nishimori identities do not hold true and a replica symmetry breaking variational principle may arise [25]. It is worth noticing that the Statistical Mechanics model described by the Hamiltonian (8) with centered interactions (which for K = 1 reduces to the standard Sherrington-Kirkpatrick model [26][27][28][29]) is still unsolved for non-convex architectures such as the deep one, see nevertheless [19,[30][31][32].…”
mentioning
confidence: 99%
“…When instead the receiver ignores the prior or the signal-to-noise ratio, only a few results are available [20][21][22][23][24]. In such settings, called mismatched, the Nishimori identities do not hold true and a replica symmetry breaking variational principle may arise [25]. It is worth noticing that the Statistical Mechanics model described by the Hamiltonian (8) with centered interactions (which for K = 1 reduces to the standard Sherrington-Kirkpatrick model [26][27][28][29]) is still unsolved for non-convex architectures such as the deep one, see nevertheless [19,[30][31][32].…”
mentioning
confidence: 99%