Leveraging machine learning features for linear optical interferometer control

• URL: http://arxiv.org/abs/2505.24032v1
• Date: Thu, 29 May 2025 22:11:17 GMT
• Title: Leveraging machine learning features for linear optical interferometer control
• Authors: Sergei S. Kuzmin, Ivan V. Dyakonov, Stanislav S. Straupe,
• Abstract summary: We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints.<n>Our algorithm employs a supervised learning approach, aligning the interferometer model with a training set derived from the device being studied.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Noise-tolerant tomography of multimode linear optical interferometers with single photons [0.0]
  We present the method for reconstructing the transfer matrix of a linear optical interferometer.<n>Our approach accounts for losses and photon indistinguishability, making it robust to experimental imperfections.<n>The results show high fidelity in matrix reconstruction and successful application in boson sampling experiments.
  arXiv  Detail & Related papers  (2025-06-25T14:36:38Z)
• New designs of linear optical interferometers with minimal depth and component count [0.0]
  We adapt an algorithm for CNOT circuits based on the Bruhat decomposition to the design of linear optical circuits with Mach-Zehnder interferometers (MZI)<n>The synthesis algorithm reduces to designing sorting networks with nearest neighbor swapping operations as elementary gates.<n>We show natural extensions of our framework for boson sampling experiments and for the coupling of multiple integrated interferometers to design larger linear optical systems.
  arXiv  Detail & Related papers  (2025-04-08T14:03:04Z)
• Inverse Surrogate Model of a Soft X-Ray Spectrometer using Domain Adaptation [0.0]
  In this study, we present a method to create a robust inverse surrogate model for a soft X-ray spectrometer.<n>Due to limited experimental data, such models are often trained with simulated data.<n>We demonstrate the application of data augmentation and adversarial domain adaptation techniques, with which we can predict absolute coordinates for the automated alignment of our spectrometer.
  arXiv  Detail & Related papers  (2025-02-21T19:42:50Z)
• Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference [47.460898983429374]
  We introduce an ensemble Kalman filter (EnKF) into the non-mean-field (NMF) variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO) We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-12-10T15:22:30Z)
• Learning Radio Environments by Differentiable Ray Tracing [56.40113938833999]
  We introduce a novel gradient-based calibration method, complemented by differentiable parametrizations of material properties, scattering and antenna patterns. We have validated our method using both synthetic data and real-world indoor channel measurements, employing a distributed multiple-input multiple-output (MIMO) channel sounder.
  arXiv  Detail & Related papers  (2023-11-30T13:50:21Z)
• Fast reconstruction of programmable integrated interferometers [0.0]
  We present a novel efficient algorithm based on linear algebra only, which does not use computationally expensive optimization procedures. We show that this approach makes it possible to perform fast and accurate characterization of high-dimensional programmable integrated interferometers.
  arXiv  Detail & Related papers  (2023-07-07T14:48:38Z)
• Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding [21.38845517949153]
  This paper presents an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear systems. We use an infinite-dimensional feature to linearly represent the state-action value function and exploits finite-dimensional truncation approximation for practical implementation.
  arXiv  Detail & Related papers  (2023-04-08T04:23:46Z)
• Retrieving space-dependent polarization transformations via near-optimal quantum process tomography [55.41644538483948]
  We investigate the application of genetic and machine learning approaches to tomographic problems. We find that the neural network-based scheme provides a significant speed-up, that may be critical in applications requiring a characterization in real-time. We expect these results to lay the groundwork for the optimization of tomographic approaches in more general quantum processes.
  arXiv  Detail & Related papers  (2022-10-27T11:37:14Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Two-colour spectrally multimode integrated SU(1,1) interferometer [77.34726150561087]
  We develop and investigate an integrated multimode two-colour SU (1,1) interferometer that operates in a supersensitive mode. By ensuring a proper design of the integrated platform, we suppress dispersion and thereby significantly increase the visibility of the interference pattern. We demonstrate that such an interferometer overcomes the classical phase sensitivity limit for wide parametric gain ranges, when up to $3*104$ photons are generated.
  arXiv  Detail & Related papers  (2022-02-10T13:30:42Z)
• Architecture agnostic algorithm for reconfigurable optical interferometer programming [0.0]
  We develop the learning algorithm to build the architecture model of the reconfigurable optical interferometer. Our algorithm adopts the supervised learning strategy which matches the model of the interferometer to the training set populated by the samples produced by the device under study.
  arXiv  Detail & Related papers  (2021-03-23T21:11:50Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Interferobot: aligning an optical interferometer by a reinforcement learning agent [118.43526477102573]
  We train an RL agent to align a Mach-Zehnder interferometer, based on images of fringes acquired by a monocular camera. The agent is trained in a simulated environment, without any hand-coded features or a priori information about the physics. Thanks to a set of domain randomizations simulating uncertainties in physical measurements, the agent successfully aligns this interferometer without any fine tuning.
  arXiv  Detail & Related papers  (2020-06-03T13:10:54Z)
• Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation [25.610534178373065]
  We consider the estimation of treatment effects in settings when multiple treatments are assigned over time. We propose an extension of the double/debiased machine learning framework to estimate the dynamic effects of treatments.
  arXiv  Detail & Related papers  (2020-02-17T22:32:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.