Leveraging machine learning features for linear optical interferometer control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuzmin, Sergei S., Dyakonov, Ivan V., Straupe, Stanislav S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918039054712832
author Kuzmin, Sergei S.
Dyakonov, Ivan V.
Straupe, Stanislav S.
author_facet Kuzmin, Sergei S.
Dyakonov, Ivan V.
Straupe, Stanislav S.
contents We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints. The programming of unitary transformations on the interferometer's optical modes relies on either an analytical method for deriving the unitary matrix from a set of phase shifts or an optimization routine when such decomposition is not available. Our algorithm employs a supervised learning approach, aligning the interferometer model with a training set derived from the device being studied. A straightforward optimization procedure leverages this trained model to determine the phase shifts of the interferometer with a specific architecture, obtaining the required unitary transformation. This approach enables the effective tuning of interferometers without requiring a precise analytical solution, paving the way for the exploration of new interferometric circuit architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging machine learning features for linear optical interferometer control
Kuzmin, Sergei S.
Dyakonov, Ivan V.
Straupe, Stanislav S.
Quantum Physics
Machine Learning
Optics
We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints. The programming of unitary transformations on the interferometer's optical modes relies on either an analytical method for deriving the unitary matrix from a set of phase shifts or an optimization routine when such decomposition is not available. Our algorithm employs a supervised learning approach, aligning the interferometer model with a training set derived from the device being studied. A straightforward optimization procedure leverages this trained model to determine the phase shifts of the interferometer with a specific architecture, obtaining the required unitary transformation. This approach enables the effective tuning of interferometers without requiring a precise analytical solution, paving the way for the exploration of new interferometric circuit architectures.
title Leveraging machine learning features for linear optical interferometer control
topic Quantum Physics
Machine Learning
Optics
url https://arxiv.org/abs/2505.24032