Linear Optical Random Projections Without Holography - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Optics Express Année : 2023

Linear Optical Random Projections Without Holography

Résumé

We introduce what we believe to be a novel method to perform linear optical random projections without the need for holography. Our method consists of a computationally trivial combination of multiple intensity measurements to mitigate the information loss usually associated with the absolute-square non-linearity imposed by optical intensity measurements. Both experimental and numerical findings demonstrate that the resulting matrix consists of real-valued, independent, and identically distributed (i.i.d.) Gaussian random entries. Our optical setup is simple and robust, as it does not require interference between two beams. We demonstrate the practical applicability of our method by performing dimensionality reduction on high-dimensional data, a common task in randomized numerical linear algebra with relevant applications in machine learning.
Fichier principal
Vignette du fichier
f8856cd8-ce08-4a9b-a96d-53dbee927723-author.pdf (314.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04261205 , version 1 (26-10-2023)

Identifiants

Citer

Ruben Ohana, Daniel Hesslow, Daniel Brunner, Sylvain Gigan, Kilian Müller. Linear Optical Random Projections Without Holography. Optics Express, 2023, 31 (16), pp.25881-25888. ⟨10.1364/OE.496224⟩. ⟨hal-04261205⟩
10 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More