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

IEEE Transactions on Quantum Engineering

Efficient Reconstruction of Wigner Function from Marginals with Deep Generative Model

Po-Hsuan Chen, Li-An Lo, Tzu-Chia Liu, YU-CHEN LEE, HONG-BIN CHEN

Published Jan 1, 2026• 0 citations
Publisher

Abstract

The Wigner function is one of the most important tools for characterizing quantum states in continuous-variable and quantum optical systems, with its negativity serving as a strong indicator of nonclassicality. However, its experimental reconstruction from measurable raw data is a tedious task requiring substantial experimental resources. On the other hand, machine learning has made immense strides and been successfully applied across various scientific disciplines. Building on our previous development of a ResNet-based deep generative model (DGM), here we further optimize the DGM to reconstruct complex Wigner functions by processing merely three experimentally measurable marginal distributions. We validate our approach using two sophisticated cavity quantum electrodynamics models, where coherent light-matter interactions introduce intricate phase-space features. Our results reveal that the DGM is capable of capturing statistical features and physical characteristics within the marginals and reproducing the intricate patterns of the Wigner functions with high accuracy. Furthermore, we demonstrate its superior performance over a widely adopted denoising diffusion model, as well as its generalizability to the time evolution of states modestly beyond the training range. Consequently, our approach is expected to substantially reduce the experimental resources required for quantum state tomography.

DOI
10.1109/tqe.2026.3748113

Related papers

Learning to Reconstruct Wigner Functions in Phase Space

Xinyu Tang, Yi-hsin Lin, Yan Zhu +5 more

Wigner function learning is a central tool for characterizing continuous variable quantum systems. A fundamental challenge in this setting is to infer a continuous phase-space function from sparse pointwise measurement data, a task that becomes increasingly demanding as the effective dimension enlarges. Here, we develop a general machine learning framework to reconstruct Wigner functions directly as continuous functions from sparse phase-space data. For states with sparse Fock-space or coherent-state representations, such as binomial code states and cat states, we devise provably efficient regression models whose measurement complexity scales only logarithmically with the effective Hilbert-space dimension. For more general states, such as the Gottesman-Kitaev-Preskill (GKP) states, we design a deep learning model that reconstructs the Wigner function from sparse measurements and generalizes to arbitrary phase-space resolution. We demonstrate the broad applicability of our framework on both simulated data and experimental data from a circuit quantum electrodynamic (circuit-QED) system. Interestingly, on experimental data, we find that our model reconstructs Wigner functions of GKP code states across multiple rounds of quantum error correction and identifies the dominant error process using significantly fewer measurements than conventional estimation techniques.

quant-pharXiv:2607.06232•Jul 8, 2026•0 citations

Unveiling the nonclassicality within quasi-distribution representations through deep learning

Hongbin Chen, Cheng‐Hua Liu, Kuan-Lun Lai +4 more

Abstract To unequivocally distinguish genuine quantumness from classicality, a widely adopted approach focuses on the negative values of a quasi-distribution representation as compelling evidence of nonclassicality. Prominent examples include the dynamical process nonclassicality characterized by the canonical Hamiltonian ensemble representation (CHER) and the nonclassicality of quantum states characterized by the Wigner function. However, to construct a multivariate joint quasi-distribution function with negative values from experimental data is typically highly cumbersome. Here we propose a computational approach utilizing a deep generative model, processing three marginals, to construct the bivariate joint quasi-distribution functions. We first apply our model to tackle the challenging problem of the CHERs, which lacks universal solutions, rendering the problem ground-truth (GT) deficient. To overcome the GT deficiency of the CHER problem, we design optimal synthetic datasets to train our model. While trained with synthetic data, the physics-informed optimization enables our model to capture the detrimental effect of the thermal fluctuations on nonclassicality, which cannot be obtained from any analytical solutions. This underscores the reliability of our approach. This approach also allows us to predict the Wigner functions subject to thermal noises. Our model predicts the Wigner functions with a prominent accuracy by processing three marginals of probability distributions. Our approach also provides a significant reduction of the experimental efforts of constructing the Wigner functions of quantum states, giving rise to an efficient alternative way to realize the quantum state tomography.

arXiv:2312.16055•Quantum Science and Technology•Nov 5, 2024•4 citations

Phase Space Insights: Wigner Functions for Qubits and Beyond

Luis Lorenzo Sánchez-Soto, Ariana S. Muñoz, Pablo de la Hoz +2 more

Phase space methods, particularly Wigner functions, provide intuitive tools for representing and analyzing quantum states. We focus on systems with SU(2) dynamical symmetry, which naturally describes spin and a wide range of two-mode quantum models. We present a unified phase space framework tailored to these systems, highlighting its broad applicability in quantum optics, metrology, and information. After reviewing the core SU(2) phase-space formalism, we apply it to states designed for optimal quantum sensing, where their nonclassical features are clearly revealed in the Wigner representation. We then extend the approach to systems with an indefinite number of excitations, introducing a generalized framework that captures correlations across multiple SU(2)-invariant subspaces. These results offer practical tools for understanding both theoretical and experimental developments in quantum science.

Applied Sciences•May 6, 2025•8 citations

Quantum state estimation based on deep learning

Haowen 皓文 Xiao 肖, Zhiguang Han

Abstract We used deep learning techniques to construct various models for reconstructing quantum states from a given set of coincidence measurements. Through simulations, we have demonstrated that our approach generates functionally equivalent reconstructed states for a wide range of pure and mixed input states. Compared with traditional methods, our system offers the advantage of faster speed. Additionally, by training our system with measurement results containing simulated noise sources, the system shows a significant improvement in average fidelity compared with typical reconstruction methods. We also found that constraining the variational manifold to physical states, i.e., positive semi-definite density matrices, greatly enhances the quality of the reconstructed states in the presence of experimental imperfections and noise. Finally, we validated the correctness and superiority of our model by using data generated on IBM Quantum Platform, a real quantum computer.

Chinese Physics B•Sep 10, 2024•1 citation

Generative Quantum Machine Learning via Denoising Diffusion Probabilistic Models

Bingzhi Zhang, Peng Xu, Xiaohui Chen +1 more

Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse and high-quality samples in many computer vision tasks, as well as to incorporate flexible model architectures and a relatively simple training scheme. Quantum generative models, empowered by entanglement and superposition, have brought new insight to learning classical and quantum data. Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic model (QuDDPM) to enable efficiently trainable generative learning of quantum data. QuDDPM adopts sufficient layers of circuits to guarantee expressivity, while it introduces multiple intermediate training tasks as interpolation between the target distribution and noise to avoid barren plateau and guarantee efficient training. We provide bounds on the learning error and demonstrate QuDDPM's capability in learning correlated quantum noise model, quantum many-body phases, and topological structure of quantum data. The results provide a paradigm for versatile and efficient quantum generative learning.

arXiv:2310.05866•Physical Review Letters•Mar 5, 2024•75 citations

Variational Autoencoder Reconstruction of Complex Many-Body Physics

I. A. Luchnikov, Alexander Ryzhov, Pieter-Jan Stas +2 more

Thermodynamics is a theory of principles that permits a basic description of the macroscopic properties of a rich variety of complex systems from traditional ones, such as crystalline solids, gases, liquids, and thermal machines, to more intricate systems such as living organisms and black holes to name a few. Physical quantities of interest, or equilibrium state variables, are linked together in equations of state to give information on the studied system, including phase transitions, as energy in the forms of work and heat, and/or matter are exchanged with its environment, thus generating entropy. A more accurate description requires different frameworks, namely, statistical mechanics and quantum physics to explore in depth the microscopic properties of physical systems and relate them to their macroscopic properties. These frameworks also allow to go beyond equilibrium situations. Given the notably increasing complexity of mathematical models to study realistic systems, and their coupling to their environment that constrains their dynamics, both analytical approaches and numerical methods that build on these models show limitations in scope or applicability. On the other hand, machine learning, i.e., data-driven, methods prove to be increasingly efficient for the study of complex quantum systems. Deep neural networks, in particular, have been successfully applied to many-body quantum dynamics simulations and to quantum matter phase characterization. In the present work, we show how to use a variational autoencoder (VAE)—a state-of-the-art tool in the field of deep learning for the simulation of probability distributions of complex systems. More precisely, we transform a quantum mechanical problem of many-body state reconstruction into a statistical problem, suitable for VAE, by using informationally complete positive operator-valued measure. We show, with the paradigmatic quantum Ising model in a transverse magnetic field, that the ground-state physics, such as, e.g., magnetization and other mean values of observables, of a whole class of quantum many-body systems can be reconstructed by using VAE learning of tomographic data for different parameters of the Hamiltonian, and even if the system undergoes a quantum phase transition. We also discuss challenges related to our approach as entropy calculations pose particular difficulties.

arXiv:1910.03957•Entropy•Nov 7, 2019•40 citations
The Wigner function is one of the most important tools for characterizing quantum states in continuous-variable and quantum optical systems, with its negativity serving as a strong indicator of nonclassicality. However, its experimental reconstruction from measurable raw data is a tedious task requiring substantial experimental resources. On the other hand, machine learning has made immense strides and been successfully applied across various scientific disciplines. Building on our previous development of a ResNet-based deep generative model (DGM), here we further optimize the DGM to reconstruct complex Wigner functions by processing merely three experimentally measurable marginal distributions. We validate our approach using two sophisticated cavity quantum electrodynamics models, where coherent light-matter interactions introduce intricate phase-space features. Our results reveal that the DGM is capable of capturing statistical features and physical characteristics within the marginals and reproducing the intricate patterns of the Wigner functions with high accuracy. Furthermore, we demonstrate its superior performance over a widely adopted denoising diffusion model, as well as its generalizability to the time evolution of states modestly beyond the training range. Consequently, our approach is expected to substantially reduce the experimental resources required for quantum state tomography.
Wigner function learning is a central tool for characterizing continuous variable quantum systems. A fundamental challenge in this setting is to infer a continuous phase-space function from sparse pointwise measurement data, a task that becomes increasingly demanding as the effective dimension enlarges. Here, we develop a general machine learning framework to reconstruct Wigner functions directly as continuous functions from sparse phase-space data. For states with sparse Fock-space or coherent-state representations, such as binomial code states and cat states, we devise provably efficient regression models whose measurement complexity scales only logarithmically with the effective Hilbert-space dimension. For more general states, such as the Gottesman-Kitaev-Preskill (GKP) states, we design a deep learning model that reconstructs the Wigner function from sparse measurements and generalizes to arbitrary phase-space resolution. We demonstrate the broad applicability of our framework on both simulated data and experimental data from a circuit quantum electrodynamic (circuit-QED) system. Interestingly, on experimental data, we find that our model reconstructs Wigner functions of GKP code states across multiple rounds of quantum error correction and identifies the dominant error process using significantly fewer measurements than conventional estimation techniques.
Abstract To unequivocally distinguish genuine quantumness from classicality, a widely adopted approach focuses on the negative values of a quasi-distribution representation as compelling evidence of nonclassicality. Prominent examples include the dynamical process nonclassicality characterized by the canonical Hamiltonian ensemble representation (CHER) and the nonclassicality of quantum states characterized by the Wigner function. However, to construct a multivariate joint quasi-distribution function with negative values from experimental data is typically highly cumbersome. Here we propose a computational approach utilizing a deep generative model, processing three marginals, to construct the bivariate joint quasi-distribution functions. We first apply our model to tackle the challenging problem of the CHERs, which lacks universal solutions, rendering the problem ground-truth (GT) deficient. To overcome the GT deficiency of the CHER problem, we design optimal synthetic datasets to train our model. While trained with synthetic data, the physics-informed optimization enables our model to capture the detrimental effect of the thermal fluctuations on nonclassicality, which cannot be obtained from any analytical solutions. This underscores the reliability of our approach. This approach also allows us to predict the Wigner functions subject to thermal noises. Our model predicts the Wigner functions with a prominent accuracy by processing three marginals of probability distributions. Our approach also provides a significant reduction of the experimental efforts of constructing the Wigner functions of quantum states, giving rise to an efficient alternative way to realize the quantum state tomography.
Phase space methods, particularly Wigner functions, provide intuitive tools for representing and analyzing quantum states. We focus on systems with SU(2) dynamical symmetry, which naturally describes spin and a wide range of two-mode quantum models. We present a unified phase space framework tailored to these systems, highlighting its broad applicability in quantum optics, metrology, and information. After reviewing the core SU(2) phase-space formalism, we apply it to states designed for optimal quantum sensing, where their nonclassical features are clearly revealed in the Wigner representation. We then extend the approach to systems with an indefinite number of excitations, introducing a generalized framework that captures correlations across multiple SU(2)-invariant subspaces. These results offer practical tools for understanding both theoretical and experimental developments in quantum science.
Abstract We used deep learning techniques to construct various models for reconstructing quantum states from a given set of coincidence measurements. Through simulations, we have demonstrated that our approach generates functionally equivalent reconstructed states for a wide range of pure and mixed input states. Compared with traditional methods, our system offers the advantage of faster speed. Additionally, by training our system with measurement results containing simulated noise sources, the system shows a significant improvement in average fidelity compared with typical reconstruction methods. We also found that constraining the variational manifold to physical states, i.e., positive semi-definite density matrices, greatly enhances the quality of the reconstructed states in the presence of experimental imperfections and noise. Finally, we validated the correctness and superiority of our model by using data generated on IBM Quantum Platform, a real quantum computer.
Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse and high-quality samples in many computer vision tasks, as well as to incorporate flexible model architectures and a relatively simple training scheme. Quantum generative models, empowered by entanglement and superposition, have brought new insight to learning classical and quantum data. Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic model (QuDDPM) to enable efficiently trainable generative learning of quantum data. QuDDPM adopts sufficient layers of circuits to guarantee expressivity, while it introduces multiple intermediate training tasks as interpolation between the target distribution and noise to avoid barren plateau and guarantee efficient training. We provide bounds on the learning error and demonstrate QuDDPM's capability in learning correlated quantum noise model, quantum many-body phases, and topological structure of quantum data. The results provide a paradigm for versatile and efficient quantum generative learning.
Thermodynamics is a theory of principles that permits a basic description of the macroscopic properties of a rich variety of complex systems from traditional ones, such as crystalline solids, gases, liquids, and thermal machines, to more intricate systems such as living organisms and black holes to name a few. Physical quantities of interest, or equilibrium state variables, are linked together in equations of state to give information on the studied system, including phase transitions, as energy in the forms of work and heat, and/or matter are exchanged with its environment, thus generating entropy. A more accurate description requires different frameworks, namely, statistical mechanics and quantum physics to explore in depth the microscopic properties of physical systems and relate them to their macroscopic properties. These frameworks also allow to go beyond equilibrium situations. Given the notably increasing complexity of mathematical models to study realistic systems, and their coupling to their environment that constrains their dynamics, both analytical approaches and numerical methods that build on these models show limitations in scope or applicability. On the other hand, machine learning, i.e., data-driven, methods prove to be increasingly efficient for the study of complex quantum systems. Deep neural networks, in particular, have been successfully applied to many-body quantum dynamics simulations and to quantum matter phase characterization. In the present work, we show how to use a variational autoencoder (VAE)—a state-of-the-art tool in the field of deep learning for the simulation of probability distributions of complex systems. More precisely, we transform a quantum mechanical problem of many-body state reconstruction into a statistical problem, suitable for VAE, by using informationally complete positive operator-valued measure. We show, with the paradigmatic quantum Ising model in a transverse magnetic field, that the ground-state physics, such as, e.g., magnetization and other mean values of observables, of a whole class of quantum many-body systems can be reconstructed by using VAE learning of tomographic data for different parameters of the Hamiltonian, and even if the system undergoes a quantum phase transition. We also discuss challenges related to our approach as entropy calculations pose particular difficulties.