Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

OSA Advanced Photonics Congress

Machine Learning in Quantum Communication

Max Rückmann, Sebastian Kleis, Christian G. Schaeffer, Darko Zibar

Published Jan 1, 2020• 1 citation
Publisher

Abstract

Phase estimation of signals below noise is a main challenge in optical quantum communication receivers. Heterodyne detection at a SNR of less than -20 dB with machine learning based optimized carrier phase estimation is demonstrated.
DOI
10.1364/sppcom.2020.sptu3i.6

Related papers

17 GBd Sub-Photon Level Heterodyne Detection for CV-QKD Enabled by Machine Learning

Max Rückmann, Sebastian Kleis, Christian G. Schaeffer

We experimentally demonstrate heterodyne detection at a SNR of less than −20 dB with machine learning based optimized carrier phase estimation. Successful 17 GBaud BPSK signal demodulation is achieved without the use of pilot signals.

Optical Fiber Communication Conference•Jan 1, 2020•3 citations

Heterodyne Receivers for Quantum Communication

Christian Schaeffer, Sebastian Kleis, Max Rückmann +1 more

Phase estimation of signals below noise is a main challenge in optical quantum communication receivers. System experiments with 1 GBaud over 26 km fiber were achieved. Laser phase noise is mitigated using Machine Learning methods.

Asia Communications and Photonics Conference•Nov 2, 2019•1 citation

A Review of the Applications of Quantum Machine Learning in Optical Communication Systems

Ark Modi, Alonso Viladomat Jasso, Roberto Ferrara +4 more

In the context of optical signal processing, quantum and quantum-inspired machine learning algorithms have massive potential for deployment. One of the applications is in error correction protocols for the received noisy signals. In some scenarios, non-linear and unknown errors can lead to noise that bypasses linear error correction protocols that optical receivers generally implement. In those cases, machine learning techniques are used to recover the transmitted signal from the received signal through various estimation procedures. Since quantum machine learning algorithms promise advantage over classical algorithms, we expect that optical signal processing can benefit from these advantages. In this review, we survey several proposed quantum and quantum-inspired machine learning algorithms and their applicability with current technology to optical signal processing.

arXiv:2309.05205•Sep 11, 2023•2 citations

Coherent optical communications enhanced by machine intelligence

Sanjaya Lohani, Ryan T Glasser

Abstract Accuracy in discriminating between different received coherent signals is integral to the operation of many free-space communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communication scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we design the neural network system such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is distributed to the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. We anticipate that these results will allow for a significant enhancement of current classical and quantum coherent optical communications technologies.

arXiv:1909.02525•Machine Learning Science and Technology•Jun 12, 2020•10 citations

Experimental Phase Estimation Enhanced by Machine Learning

Alessandro Lumino, Emanuele Polino, Adil S. Rab +4 more

Phase estimation has applications from quantum imaging to gravitational-wave detection. In areas such as biological-system sampling or quantum metrology, it is crucial to optimally acquire information from a very limited number of probes. To address this need, the authors describe and experimentally verify a machine-learning method for optimal adaptive single-photon phase estimation based on a small number of trials. This approach could be used to optimize quantum metrology protocols, and can be extended to general multiparameter scenarios.

arXiv:1712.07570•Physical Review Applied•Oct 12, 2018•105 citations

Multiphoton optical heterodyne detection

Malvin Carl Teich

After reviewing recent work on multiphoton direct detection and single-photon heterodyne detection, we examine the behavior of a multiphoton absorption heterodyne receiver. Expressions are obtained for the detector response, signal-to-noise ratio (SNR), and minimum detectable power for a number of cases of interest. Receiver performance is found to depend on the higher order correlation functions of the radiation field and on the local oscillator (LO) irradiance. Although performance similar to that of the single-photon heterodyne receiver can theoretically be achieved, practical problems would appear to make this difficult. A physical interpretation of the process in terms of the absorption of monochromatic and nonmonochromatic photons is given. The double-quantum case is treated in particular detail; the results of a preliminary experiment are presented and suggestions for future experiments are provided.

IEEE Journal of Quantum Electronics•Aug 1, 1975•7 citations
In the context of optical signal processing, quantum and quantum-inspired machine learning algorithms have massive potential for deployment. One of the applications is in error correction protocols for the received noisy signals. In some scenarios, non-linear and unknown errors can lead to noise that bypasses linear error correction protocols that optical receivers generally implement. In those cases, machine learning techniques are used to recover the transmitted signal from the received signal through various estimation procedures. Since quantum machine learning algorithms promise advantage over classical algorithms, we expect that optical signal processing can benefit from these advantages. In this review, we survey several proposed quantum and quantum-inspired machine learning algorithms and their applicability with current technology to optical signal processing.
Abstract Accuracy in discriminating between different received coherent signals is integral to the operation of many free-space communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communication scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we design the neural network system such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is distributed to the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. We anticipate that these results will allow for a significant enhancement of current classical and quantum coherent optical communications technologies.
Phase estimation has applications from quantum imaging to gravitational-wave detection. In areas such as biological-system sampling or quantum metrology, it is crucial to optimally acquire information from a very limited number of probes. To address this need, the authors describe and experimentally verify a machine-learning method for optimal adaptive single-photon phase estimation based on a small number of trials. This approach could be used to optimize quantum metrology protocols, and can be extended to general multiparameter scenarios.
After reviewing recent work on multiphoton direct detection and single-photon heterodyne detection, we examine the behavior of a multiphoton absorption heterodyne receiver. Expressions are obtained for the detector response, signal-to-noise ratio (SNR), and minimum detectable power for a number of cases of interest. Receiver performance is found to depend on the higher order correlation functions of the radiation field and on the local oscillator (LO) irradiance. Although performance similar to that of the single-photon heterodyne receiver can theoretically be achieved, practical problems would appear to make this difficult. A physical interpretation of the process in terms of the absorption of monochromatic and nonmonochromatic photons is given. The double-quantum case is treated in particular detail; the results of a preliminary experiment are presented and suggestions for future experiments are provided.