Fundamental limits of detection in the spiked Wigner model (Q2196197)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Fundamental limits of detection in the spiked Wigner model |
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Fundamental limits of detection in the spiked Wigner model |
scientific article |
Statements
Fundamental limits of detection in the spiked Wigner model (English)
0 references
28 August 2020
0 references
One of the fundamental tasks in machine learning is low-rank information extraction from a noise-corrupted data matrix. This paper deals with the fundamental limits of spike detection in the rank-one spiked Wigner model. It is proved that the logarithm of the likelihood ratio has Gaussian fluctuations below the reconstruction threshold.
0 references
contiguity
0 references
hypothesis testing
0 references
Sherrington-Kirkpatrick model
0 references
replica-symmetry
0 references
random matrix models
0 references
spin-glasses
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0.8089017271995544
0 references
0.8005329966545105
0 references
0.7800256013870239
0 references
0.7699087858200073
0 references
0.7608415484428406
0 references
