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

arXiv:2311.07203 · Physical Review Research

Optical quantum sensing for agnostic environments via deep learning

Z.-F. Zhou, Yuxuan Du, Xu-Fei Yin, Shanshan Zhao, Xinmei Tian, Dacheng Tao

Published Dec 12, 2024• 4 citations
arXivHTMLPDF

Abstract

Optical quantum sensing promises measurement precision beyond classical sensors termed the Heisenberg limit (HL). However, conventional methodologies often rely on prior knowledge of the target system to achieve HL, presenting challenges in practical applications. Addressing this limitation, we introduce an innovative deep-learning-based quantum sensing scheme (DQS), enabling optical quantum sensors to attain HL in agnostic environments. DQS incorporates two essential components: a graph neural network (GNN) predictor and a trigonometric interpolation algorithm. Operating within a data-driven paradigm, DQS utilizes the GNN predictor, trained on offline data, to unveil the intrinsic relationships between the optical setups employed in preparing the probe state and the resulting quantum Fisher information (QFI) after interaction with the agnostic environment. This distilled knowledge facilitates the identification of optimal optical setups associated with maximal QFI. Subsequently, DQS employs a trigonometric interpolation algorithm to recover the unknown parameter estimates for the identified optical setups. Extensive experiments are conducted to investigate the performance of DQS under different settings up to eight photons. Our findings not only offer a different lens through which to accelerate optical quantum sensing tasks but also catalyze future research integrating deep learning and quantum mechanics. Published by the American Physical Society 2024

DOI
10.1103/physrevresearch.6.043267

Related papers

All-optical Loss-tolerant Distributed Quantum Sensing

Rajveer Nehra, Changhun Oh, Liang Jiang +1 more

Distributed quantum sensing (DQS) leverages quantum resources to estimate an unknown global property of a networked quantum sensor beyond the classical limit. We propose and analyze an all-optical resource-efficient scheme for the next-generation DQS systems. Our method utilizes phase-sensitive optical parametric amplifiers and linear interferometers and achieves the sensitivity close to the optimal limit, as determined by the quantum Fisher information of the entangled resource state. Furthermore, it utilizes high-gain OPA-assisted detection, offering critical advantages of increased bandwidth and loss tolerance, in contrast to conventional methods employing balanced homodyne detection (BHD). We show the efficacy of our proposal for displacement sensing and show its loss tolerance against high levels of photon loss, thus circumventing the major obstacle in current BHD-based approaches. Our architectural analysis shows that our scheme can be realized with current quantum photonic technology

arXiv:2407.13654•Jul 18, 2024•0 citations

All-optical Loss-tolerant Distributed Quantum Sensing

Rajveer Nehra, Changhun Oh, Liang Jiang +1 more

Abstract Distributed quantum sensing (DQS) leverages quantum resources to estimate an unknown global property of a networked quantum sensor beyond the classical limit. We propose and analyze an all-optical resource-efficient scheme for the next-generation DQS systems. Our method utilizes phase-sensitive optical parametric amplifiers (OPAs) and linear interferometers and achieves the sensitivity close to the optimal limit, as determined by the quantum Fisher information of the entangled resource state. Furthermore, it utilizes high-gain OPA-assisted detection, offering critical advantages of increased bandwidth and loss tolerance, in contrast to conventional methods employing balanced homodyne detection (BHD). We show the efficacy of our proposal for displacement sensing and show its loss tolerance against high levels of photon loss, thus circumventing the major obstacle in current BHD-based approaches. Our architectural analysis shows that our scheme can be realized with current quantum photonic technology.

•Nov 8, 2024•0 citations

Advances in Optical Metrology: The Impact of Deep Learning and Quantum Photonics

Rea Bitri, Maaruf Ali

There have been numerous advances in the fields of engineering, medicine, environment and so forth that involve measurements as a critical part of research and applications. Especially, when it comes to reaching efficient and precision measurements - what comes in handy are optical sensors that provide results beyond just size or location. In recent years, research have primarily relied on providing solutions by using deep learning and novel training algorithms for efficiently determining and eliciting results in the fields that optical metrology is applied. However, there is also analysed optical quantum metrology that is bringing a new finding to light. This paper will analyse the impact of deep learning in quantum metrology and will provide future suggestions on how to improve the results in terms of classical means by using the technologies of quantum photonics metrology to provide actual examples and applications of both technologies in real life.

International Conference on Computing, Electronics & Communications Engineering (iCCECE)•Aug 14, 2023•1 citation

The utilization of photonic neural networks in the domain of quantum sensing

Alexander Y. Grebeshkov

Quantum sensing is a quantum-based process that concerns the development of principles, methods, and devices using superposition of quantum states. Quantum sensors find application in a variety of contexts, serving as a base sensitive element in high-precision synchronization systems, functioning as a key part of gravitometers, accelerometers, and electric and magnetic field sensors. They are also being utilized in quantum metrology and lidar technology. The data generated by quantum sensors can be employed for machine learning purposes. A discussed approach involves the direct utilization of quantum sensor data as input parameters in machine learning models based on photonic neural networks. It has been determined that there is an actual problem of integration for results from quantum sensing and photonic neural networks features. A photonic neural network is discussed as a hardware-implemented algorithm, that belongs to the category of artificial intelligence algorithms in general. The hardware-implemented algorithm reveals a complex interconnection between physical processes at the photonic-based neurons. This paper provides an analysis of quantum sensing in general. It discusses the main type of photonic neural networks and their applications for quantum sensing. The paper considers an integration scheme for photonic neural networks for key points control of quantum sensing processes. Furthermore, the paper presents a proposed functional scheme for quantum sensing control based on the regulator with photonic neural networks.

Optical Technologies for Telecommunications (OTT)•Aug 14, 2025•1 citation

Variational Methods in Optical Quantum Machine Learning

Marco Simonetti, Damiano Perri, Osvaldo Gervasi

The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding of complex systems. Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. As a case study, we considered the binary classification of points belonging to a certain geometric pattern (the Two-Moons Classification problem) on a plane. We think it is reasonable to expect benefits from using hybrid deep learning systems (classical + quantum), not just in terms of accelerating computation but also in understanding the underlying phenomena and mechanisms. This will result in the development of new machine-learning paradigms and a significant advancement in the field of quantum computation. The selected dataset is a set of 2D points creating two interleaved semicircles and is based on a 2D binary classification generator, which aids in evaluating the performance of particular methods. The two coordinates of each unique point,x1andx2, serve as the features since they present two disparate data sets in a two-dimensional representation space. The goal was to create a quantum deep neural network that could recognise and categorise points accurately with the fewest trainable parameters possible.

IEEE Access•Jan 1, 2023•7 citations

Hamiltonian learning via inverse physics-informed neural networks

Jie Liu, Xin Wang

Hamiltonian learning (HL), enabling precise estimation of system parameters and underlying dynamics, plays a critical role in characterizing quantum systems. However, conventional HL methods face challenges in noise robustness and resource efficiency, especially under limited measurements. In this work, we present Inverse Physics-Informed Neural Networks for Hamiltonian Learning (iPINN-HL), an approach that incorporates the Schrödinger equation as a soft constraint via a loss function penalty into the ML procedure. This formulation allows the model to integrate both observational data and known physical laws to infer Hamiltonian parameters with greater accuracy and resource efficiency. We benchmark iPINN-HL against a deep-neural-network-based quantum state tomography method [denoted as DNN-HL (Deep Neural Network for Hamiltonian Learning)] and demonstrate its effectiveness across several different scenarios, including one-dimensional spin chains, cross-resonance gate calibration, crosstalk identification, and real-time compensation to parameter drift. Our results show that iPINN-HL can approach the Heisenberg limit and exhibits robustness to noises, while outperforming DNN-HL in accuracy and resource efficiency. Therefore, iPINN-HL is a powerful and flexible framework for quantum system characterization for practical tasks.

arXiv:2506.10379•Physical Review Research•Oct 6, 2025•1 citation
Optical quantum sensing promises measurement precision beyond classical sensors termed the Heisenberg limit (HL). However, conventional methodologies often rely on prior knowledge of the target system to achieve HL, presenting challenges in practical applications. Addressing this limitation, we introduce an innovative deep-learning-based quantum sensing scheme (DQS), enabling optical quantum sensors to attain HL in agnostic environments. DQS incorporates two essential components: a graph neural network (GNN) predictor and a trigonometric interpolation algorithm. Operating within a data-driven paradigm, DQS utilizes the GNN predictor, trained on offline data, to unveil the intrinsic relationships between the optical setups employed in preparing the probe state and the resulting quantum Fisher information (QFI) after interaction with the agnostic environment. This distilled knowledge facilitates the identification of optimal optical setups associated with maximal QFI. Subsequently, DQS employs a trigonometric interpolation algorithm to recover the unknown parameter estimates for the identified optical setups. Extensive experiments are conducted to investigate the performance of DQS under different settings up to eight photons. Our findings not only offer a different lens through which to accelerate optical quantum sensing tasks but also catalyze future research integrating deep learning and quantum mechanics. Published by the American Physical Society 2024
Distributed quantum sensing (DQS) leverages quantum resources to estimate an unknown global property of a networked quantum sensor beyond the classical limit. We propose and analyze an all-optical resource-efficient scheme for the next-generation DQS systems. Our method utilizes phase-sensitive optical parametric amplifiers and linear interferometers and achieves the sensitivity close to the optimal limit, as determined by the quantum Fisher information of the entangled resource state. Furthermore, it utilizes high-gain OPA-assisted detection, offering critical advantages of increased bandwidth and loss tolerance, in contrast to conventional methods employing balanced homodyne detection (BHD). We show the efficacy of our proposal for displacement sensing and show its loss tolerance against high levels of photon loss, thus circumventing the major obstacle in current BHD-based approaches. Our architectural analysis shows that our scheme can be realized with current quantum photonic technology
Abstract Distributed quantum sensing (DQS) leverages quantum resources to estimate an unknown global property of a networked quantum sensor beyond the classical limit. We propose and analyze an all-optical resource-efficient scheme for the next-generation DQS systems. Our method utilizes phase-sensitive optical parametric amplifiers (OPAs) and linear interferometers and achieves the sensitivity close to the optimal limit, as determined by the quantum Fisher information of the entangled resource state. Furthermore, it utilizes high-gain OPA-assisted detection, offering critical advantages of increased bandwidth and loss tolerance, in contrast to conventional methods employing balanced homodyne detection (BHD). We show the efficacy of our proposal for displacement sensing and show its loss tolerance against high levels of photon loss, thus circumventing the major obstacle in current BHD-based approaches. Our architectural analysis shows that our scheme can be realized with current quantum photonic technology.
There have been numerous advances in the fields of engineering, medicine, environment and so forth that involve measurements as a critical part of research and applications. Especially, when it comes to reaching efficient and precision measurements - what comes in handy are optical sensors that provide results beyond just size or location. In recent years, research have primarily relied on providing solutions by using deep learning and novel training algorithms for efficiently determining and eliciting results in the fields that optical metrology is applied. However, there is also analysed optical quantum metrology that is bringing a new finding to light. This paper will analyse the impact of deep learning in quantum metrology and will provide future suggestions on how to improve the results in terms of classical means by using the technologies of quantum photonics metrology to provide actual examples and applications of both technologies in real life.
Quantum sensing is a quantum-based process that concerns the development of principles, methods, and devices using superposition of quantum states. Quantum sensors find application in a variety of contexts, serving as a base sensitive element in high-precision synchronization systems, functioning as a key part of gravitometers, accelerometers, and electric and magnetic field sensors. They are also being utilized in quantum metrology and lidar technology. The data generated by quantum sensors can be employed for machine learning purposes. A discussed approach involves the direct utilization of quantum sensor data as input parameters in machine learning models based on photonic neural networks. It has been determined that there is an actual problem of integration for results from quantum sensing and photonic neural networks features. A photonic neural network is discussed as a hardware-implemented algorithm, that belongs to the category of artificial intelligence algorithms in general. The hardware-implemented algorithm reveals a complex interconnection between physical processes at the photonic-based neurons. This paper provides an analysis of quantum sensing in general. It discusses the main type of photonic neural networks and their applications for quantum sensing. The paper considers an integration scheme for photonic neural networks for key points control of quantum sensing processes. Furthermore, the paper presents a proposed functional scheme for quantum sensing control based on the regulator with photonic neural networks.
The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum Computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding of complex systems. Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. As a case study, we considered the binary classification of points belonging to a certain geometric pattern (the Two-Moons Classification problem) on a plane. We think it is reasonable to expect benefits from using hybrid deep learning systems (classical + quantum), not just in terms of accelerating computation but also in understanding the underlying phenomena and mechanisms. This will result in the development of new machine-learning paradigms and a significant advancement in the field of quantum computation. The selected dataset is a set of 2D points creating two interleaved semicircles and is based on a 2D binary classification generator, which aids in evaluating the performance of particular methods. The two coordinates of each unique point,x1andx2, serve as the features since they present two disparate data sets in a two-dimensional representation space. The goal was to create a quantum deep neural network that could recognise and categorise points accurately with the fewest trainable parameters possible.
Hamiltonian learning (HL), enabling precise estimation of system parameters and underlying dynamics, plays a critical role in characterizing quantum systems. However, conventional HL methods face challenges in noise robustness and resource efficiency, especially under limited measurements. In this work, we present Inverse Physics-Informed Neural Networks for Hamiltonian Learning (iPINN-HL), an approach that incorporates the Schrödinger equation as a soft constraint via a loss function penalty into the ML procedure. This formulation allows the model to integrate both observational data and known physical laws to infer Hamiltonian parameters with greater accuracy and resource efficiency. We benchmark iPINN-HL against a deep-neural-network-based quantum state tomography method [denoted as DNN-HL (Deep Neural Network for Hamiltonian Learning)] and demonstrate its effectiveness across several different scenarios, including one-dimensional spin chains, cross-resonance gate calibration, crosstalk identification, and real-time compensation to parameter drift. Our results show that iPINN-HL can approach the Heisenberg limit and exhibits robustness to noises, while outperforming DNN-HL in accuracy and resource efficiency. Therefore, iPINN-HL is a powerful and flexible framework for quantum system characterization for practical tasks.