Paper: arXiv 2507.22035

Authors: David Dechant, Eliot Schwander, Lucas van Drooge, Charles Moussa, Diego Garlaschelli, Vedran Dunjko, Jordi Tura

Abstract

Quantum generative adversarial networks (QGANs) have been investigated as a method for generating synthetic data with the goal of augmenting training data sets for neural networks. This is especially relevant for financial time series, since we only ever observe one realization of the process, namely the historical evolution of the market, which is further limited by data availability and the age of the market. However, for classical generative adversarial networks it has been shown that generated data may (often) not exhibit desired properties (also called stylized facts), such as matching a certain distribution or showing specific temporal correlations. Here, we investigate whether quantum correlations in quantum inspired models of QGANs can help in the generation of financial time series. We train QGANs, composed of a quantum generator and a classical discriminator, and investigate two approaches for simulating the quantum generator: a full simulation of the quantum circuits, and an approximate simulation using tensor network methods. We tested how the choice of hyperparameters, such as the circuit depth and bond dimensions, influenced the quality of the generated time series. The QGAN that we trained generate synthetic financial time series that not only match the target distribution but also exhibit the desired temporal correlations, with the quality of each property depending on the hyperparameters and simulation method.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 4.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper employs advanced quantum information concepts, variational quantum algorithms, and tensor network methods (MPS) requiring significant mathematical abstraction, while its validation relies primarily on qualitative comparison of simulated time series against stylized facts rather than on live backtesting or extensive statistical benchmarking against real market data.

Research Flowchart

  flowchart TD
  A["Research Goal: Can Quantum Correlations<br>Generate Financial Time Series with<br>Temporal Properties?"] --> B["Methodology: Quantum Generative<br>Adversarial Network"]
  B --> C{"Simulation Methods"}
  C --> D["Full Quantum Circuit Simulation"]
  C --> E["Tensor Network Approximation"]
  B --> F["Data Input: Historical Financial<br>Equity Time Series"]
  F --> G["Training Process: Generator creates<br>synthetic data; Discriminator classifies<br>real vs. synthetic. Hyperparameters<br>varied: Circuit Depth & Bond Dimension."]
  G --> H["Key Findings: QGANs successfully<br>generate data matching target<br>distribution and temporal correlations.<br>Quality depends on hyperparameters<br>and simulation method."]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a Wasserstein quantum generative adversarial network (QGAN) that uses a parameterized quantum circuit as a generator (expectation‑value sampler) and a classical convolutional neural network as a discriminator to generate synthetic financial time series.

Source sentence
IMPLEMENTATION For this paper, we trained a Wasserstein QGAN for generating time series based on training data originating in the time series of the S&P 500 index. We use a hybrid approach, with a classical neural network as a discrimi-nator and a parameterized quantum circuit (PQC) as a generator.

Assumes 6

  • The expectation values of single‑qubit Pauli‑X and Pauli‑Z operators are interpreted as the log return of the index at each time step. model
    Source sentence
    The discrete time series spans from 20 to 40 points in time, where the expectation value of single-qubit Pauli-X and Pauli-Z operators is interpreted as the log return of the value of the index at each time step.
  • Matrix product state (MPS) simulations can efficiently approximate longer time series by exploiting linear structures. model
    Source sentence
    While full-state sim-ulations are limited to short time intervals due to their exponential scaling, MPS simulations enable us to model longer time series by exploiting their ability to efficiently replicate linear structures such as financial time series.
  • Increasing the bond dimension balances computational cost against simulation accuracy. model
    Source sentence
    In the MPS simulations, we vary the bond dimension (also referred to as the tensor train rank) to balance compu-tational costs and simulation accuracy.
  • Training data are normalized to zero mean and unit variance before model training. data
    Source sentence
    (i) We normalize our training data to have a mean of 0 and a variance of 1: rt,(i) := rt −µr σr , (12) where rt is the original log returns, and µr and σr esti-mate the mean and standard deviation of all log returns.
Show 2 more
  • An inverse Lambert‑W transform is applied to heavy‑tailed log returns to bring them closer to a Gaussian distribution. data
    Source sentence
    (ii) As learning a heavy-tailed distribution can be chal-lenging due to a limited number of samples in the tails, we implement the inverse Lambert-W transform on the normalized log returns.
  • The Wasserstein distance computed over the aggregated time‑series distribution is sufficient for training the QGAN. statistical
    Source sentence
    This approach leverages the PQC architecture to intrinsically capture temporal correlations in the time series, while the training itself is performed solely on the Wasserstein distance computed over the ag-gregated time series distribution.

Data

  • S&P 500 index log returns market-prices public
    S&P 500
    Source sentence
    In this work, we develop a quantum GAN for syn-thetic data generation and examine its ability in gen-erating time series replicating the S&P 500 index, in-cluding its distribution and temporal correlations. An example of a financial time series is the S&P 500 in-dex, which includes 500 of most valuable companies that are listed on US stock exchanges [25].

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • The trained QGAN generates synthetic time series that match the target distribution and exhibit temporal correlations such as volatility clustering. performance
    Source sentence
    The QGAN that we trained generate synthetic financial time series that not only match the target distribution but also exhibit the desired temporal correlations, with the quality of each property depending on the hyperparameters and simulation method. Our trained QGANs generate time series that match the desired distributions and exhibiting some of the tempo-ral correlations seen in financial time series, such as in
  • MPS simulations with higher bond dimensions and more layers enable training of longer time series compared to full‑state simulations. performance
    Source sentence
    The lat-ter approach allowed us to simulate PQCs with a higher number of layers and qubits, which makes it possible to train the generation of longer time series. Simulating the PQC with full-state simulations and MPS simulations yield different results, with circuit depth and the MPS bond dimension further influencing the performance.
  • Fidelity between full‑state and MPS approximations increases with bond dimension, indicating improved accuracy. statistical
    Source sentence
    As shown in Figure 4, the fidelity increases with χ, indicating improved approxima-tion accuracy.
  • Generated series from the MPS‑simulated QGAN shows positive, decreasing absolute autocorrelation (volatility clustering) closer to the S&P 500 behavior. performance figure from elsewhere in the paper
    Source sentence
    In contrast to the time series generated with the full-state simulation shown in Figure 5, the absolute autocorrelation (Subfigure (d)) that indicates volatility clustering is positive and decreasing for all time lags.
  • Circuit depth and MPS bond dimension further influence the quality of generated distribution and temporal‑correlation metrics. performance
    Source sentence
    Simulating the PQC with full-state simulations and MPS simulations yield different results, with circuit depth and the MPS bond dimension further influencing the performance.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 30 related papers). Coverage is partial, so this is neither replication nor refutation.

Cited by 1 paper in the archive (1 by independent authors)

Code

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (99)

  1. JAX : composable transformations of P ython+ N um P y programs (2018) — link
  2. S& P 500 \textregistered (2025)
  3. The Computational Complexity of Linear Optics (2013) — link
  4. TensorFlow : A System for Large-Scale Machine Learning (2016)
  5. The Power of Quantum Neural Networks (2021) — link
  6. Noise Robustness and Experimental Demonstration of a Quantum Generative Adversarial Network for Continuous Distributions (2021) — link
  7. Wasserstein Generative Adversarial Networks (2017)
  8. Generating Synthetic Data in Finance : Opportunities , Challenges and Pitfalls (2020) — link
and 91 more
  1. Data Augmentation Experiments with Style-Based Quantum Generative Adversarial Networks on Trapped-Ion and Superconducting-Qubit Technologies (2024) — link
  2. Parameterized Quantum Circuits as Universal Generative Models for Continuous Multivariate Distributions (2024) — link
  3. Parameterized Quantum Circuits as Universal Generative Models for Continuous Multivariate Distributions (2024) — link
  4. Order p Quantum Wasserstein Distances from Couplings (2025) — link
  5. A Generative Modeling Approach for Benchmarking and Training Shallow Quantum Circuits (2018) — link
  6. Tensor Networks for Quantum Computing (2025) — link
  7. The Pricing of Options and Corporate Liabilities (1973) — link
  8. Trapped-Ion Quantum Computing: Progress and Challenges (2019)
  9. Variational Quantum Algorithms (2021)
  10. Quantum Wasserstein Generative Adversarial Networks (2019)
  11. Quantum Long Short-Term Memory (2022) — link
  12. Quantum Computations with Cold Trapped Ions (1995) — link
  13. Matrix Product States and Projected Entangled Pair States: Concepts , Symmetries, Theorems (2021) — link
  14. Superconducting Quantum Bits (2008)
  15. Empirical Properties of Asset Returns: Stylized Facts and Statistical Issues (2001) — link
  16. Quantum versus Classical Generative Modelling in Finance (2021) — link
  17. Quantum Generative Adversarial Networks (2018) — link
  18. Error and Resource Estimates of Variational Quantum Algorithms for Solving Differential Equations Based on Runge-Kutta Methods (2024) — link
  19. Quantum Computing for High-Energy Physics : State of the Art and Challenges (2024) — link
  20. Machine Learning in Finance : From Theory to Practice (2020) — link
  21. Generation of Realistic Synthetic Financial Time-series (2022) — link
  22. Data Augmentation Using GANs (2019)
  23. Generative Adversarial Networks in Finance: An Overview (2021) — link
  24. A Hybrid Quantum Wasserstein GAN with Applications to Option Pricing (2023) — link
  25. The Lambert Way to Gaussianize Heavy-Tailed Data with the Inverse of Tukey ’s h Transformation as a Special Case (2015) — link
  26. Generative Adversarial Nets (2014)
  27. Generative Adversarial Networks (2020) — link
  28. Quimb: A Python Package for Quantum Information and Many-Body Calculations (2018) — link
  29. A Review on Generative Adversarial Networks: Algorithms , Theory, and Applications (2021)
  30. Improved Training of Wasserstein Gans (2017)
  31. Quantum Computing with Neutral Atoms (2020)
  32. Anomaly Detection with Variational Quantum Generative Adversarial Networks (2021) — link
  33. WGAN Financial Time-Series (2025) — link
  34. Experimental Quantum Generative Adversarial Networks for Image Generation (2021) — link
  35. A Survey on Superconducting Computing Technology: Circuits, Architectures and Design Tools (2022)
  36. Quantum Information Processing Using Quantum Dot Spins and Cavity QED (1999) — link
  37. Hardware-Efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets (2017)
  38. Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry (2023) — link
  39. Progressive Growing of GANs for Improved Quality , Stability , and Variation (2018) — link
  40. A Style-Based Generator Architecture for Generative Adversarial Networks (2019)
  41. Learning Quantum Data with the Quantum Earth Mover’s Distance (2022) — link
  42. A Scheme for Efficient Quantum Computation with Linear Optics (2001)
  43. Quantum Computing for Generative Modeling and Applications (2023) — link
  44. Barren Plateaus in Variational Quantum Computing (2025)
  45. Differentiable Learning of Quantum Circuit Born Machine (2018) — link
  46. Quantum Generative Adversarial Learning (2018) — link
  47. Community Detection for Correlation Matrices (2015) — link
  48. Quantum Machine Learning Advantages beyond Hardness of Evaluation (2025) — link
  49. Contextual Quantum Neural Networks for Stock Price Prediction (2025) — link
  50. A Survey of Recent Advances in Quantum Generative Adversarial Networks (2023) — link
  51. Entangling Quantum Generative Adversarial Networks (2022) — link
  52. Enhancing Financial Time Series Prediction with Quantum-Enhanced Synthetic Data Generation : A Case Study on the S & P 500 Using a Quantum Wasserstein Generative Adversarial Network Approach with a Gradient Penalty (2024) — link
  53. Tensor- Train Decomposition (2011) — link
  54. Thermodynamic Limit of Density Matrix Renormalization (1995) — link
  55. QuantumLeap : Hybrid Quantum Neural Network for Financial Predictions (2022) — link
  56. Synthetic Data Generation with Hybrid Quantum-Classical Models for the Financial Sector (2024) — link
  57. Synthetic Data Applications in Finance (2024) — link
  58. Quantum Computing in the NISQ Era and Beyond (2018) — link
  59. Understanding Deep Learning (2023)
  60. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (2016) — link
  61. Quantum Computational Finance: Monte Carlo Pricing of Financial Derivatives (2018) — link
  62. Tensor Networks for Quantum Machine Learning (2023) — link
  63. A Universal Qudit Quantum Processor with Trapped Ions (2022) — link
  64. Variational Quantum Generators : Generative Adversarial Quantum Machine Learning for Continuous Distributions (2021) — link
  65. Trainability Barriers and Opportunities in Quantum Generative Modeling (2024) — link
  66. Generative Adversarial Networks ( GANs ): Challenges , Solutions , and Future Directions (2022) — link
  67. Quantum Generative Modelling for Financial Time Series (2022) — link
  68. Shadow- Frugal Expectation-Value-Sampling Variational Quantum Generative Model (2024)
  69. Shadow- Frugal Expectation-Value-Sampling Variational Quantum Generative Model (2024) — link
  70. Effects of Observable Choices in the Performance of Variational Quantum Generative Models - CONFIDENTIAL (2024)
  71. A Survey on Image Data Augmentation for Deep Learning (2019) — link
  72. MosaiQ : Quantum Generative Adversarial Networks for Image Generation on NISQ Computers (2023)
  73. Quantum Generative Adversarial Network for Generating Discrete Distribution (2020) — link
  74. On the Quantum versus Classical Learnability of Discrete Distributions (2021) — link
  75. Modeling Financial Time-Series with Generative Adversarial Networks (2019) — link
  76. Generation of Synthetic Financial Time Series by Diffusion Models — → 2410.18897
  77. Data Augmentation Using GANs (2019) — link
  78. Recent Advances for Quantum Neural Networks in Generative Learning (2022) — link
  79. Hybrid Quantum – Classical Generative Adversarial Network for High-Resolution Image Generation (2023) — link
  80. Analysis of Financial Time Series
  81. Density Matrix Renormalization Group and Periodic Boundary Conditions : A Quantum Information Perspective (2004) — link
  82. Matrix Product States, Projected Entangled Pair States, and Variational Renormalization Group Methods for Quantum Spin Systems (2008) — link
  83. The Wasserstein Distances (2009) — link
  84. Qudits and High-Dimensional Quantum Computing (2020) — link
  85. Quant GANs : Deep Generation of Financial Time Series (2020) — link
  86. Quantum Reinforcement Learning of Classical Rare Dynamics: Enhancement by Intrinsic Fourier Features (2025) — link
  87. Quantum Risk Analysis (2019) — link
  88. Stock Market Prediction Based on Generative Adversarial Network (2019) — link
  89. Hybrid Quantum–Classical Generative Adversarial Networks for Image Generation via Learning Discrete Distribution (2023) — link
  90. Quantum Generative Adversarial Networks for Learning and Loading Random Distributions (2019) — link
  91. Time series (1975)

1 of 99 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.