Exponential capacity scaling of classical GANs compared to hybrid latent style-based quantum GANs

• URL: http://arxiv.org/abs/2601.05036v1
• Date: Thu, 08 Jan 2026 15:44:41 GMT
• Title: Exponential capacity scaling of classical GANs compared to hybrid latent style-based quantum GANs
• Authors: Milan Liepelt, Julien Baglio,
• Abstract summary: Quantum generative adversarial networks (QGANs) are leading candidates for quantum generative modeling.<n>The latent style-based QGAN, relying on a classical variational autoencoder to encode the input data into a latent space has been proven to be efficient for image generation or drug design.<n>We present in this work the first comprehensive experimental analysis of this advantage of QGANS applied to SAT4 image generation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum generative modeling is a very active area of research in looking for practical advantage in data analysis. Quantum generative adversarial networks (QGANs) are leading candidates for quantum generative modeling and have been applied to diverse areas, from high-energy physics to image generation. The latent style-based QGAN, relying on a classical variational autoencoder to encode the input data into a latent space and then using a style-based QGAN for data generation has been proven to be efficient for image generation or drug design, hinting at the use of far less trainable parameters than their classical counterpart to achieve comparable performance, however this advantage has never been systematically studied. We present in this work the first comprehensive experimental analysis of this advantage of QGANS applied to SAT4 image generation, obtaining an exponential advantage in capacity scaling for a quantum generator in the hybrid latent style-based QGAN architecture. Careful tuning of the autoencoder is crucial to obtain stable, reliable results. Once this tuning is performed and defining training optimality as when the training is stable and the FID score is low and stable as well, the optimal capacity (or number of trainable parameters) of the classical discriminator scales exponentially with respect to the capacity of the quantum generator, and the same is true for the capacity of the classical generator. This hints toward a type of quantum advantage for quantum generative modeling.

Related papers

• Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning [0.0]
  Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images.<n>In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning.<n>Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality.
  arXiv  Detail & Related papers  (2025-07-13T16:46:56Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Flowing Through Hilbert Space: Quantum-Enhanced Generative Models for Lattice Field Theory [0.9208007322096533]
  We develop a hybrid quantum-classical normalizing flow model to explore quantum-enhanced sampling in such regimes.<n>Our approach embeds parameterized quantum circuits within a classical normalizing flow architecture, leveraging amplitude encoding and quantum entanglement to enhance expressivity in the generative process.
  arXiv  Detail & Related papers  (2025-05-15T17:58:16Z)
• LatentQGAN: A Hybrid QGAN with Classical Convolutional Autoencoder [7.945302052915863]
  A potential application of quantum machine learning is to harness the power of quantum computers for generating classical data. We propose LatentQGAN, a novel quantum model that uses a hybrid quantum-classical GAN coupled with an autoencoder.
  arXiv  Detail & Related papers  (2024-09-22T23:18:06Z)
• Latent Style-based Quantum GAN for high-quality Image Generation [28.3231031892146]
  We introduce the Latent Style-based Quantum GAN (LaSt-QGAN), which employs a hybrid classical-quantum approach in training Generative Adversarial Networks (GANs) Our LaSt-QGAN can be successfully trained on realistic computer vision datasets beyond the standard MNIST, namely Fashion MNIST (fashion products) and SAT4 (Earth Observation images) with 10 qubits.
  arXiv  Detail & Related papers  (2024-06-04T18:00:00Z)
• Towards Efficient Quantum Hybrid Diffusion Models [68.43405413443175]
  We propose a new methodology to design quantum hybrid diffusion models. We propose two possible hybridization schemes combining quantum computing's superior generalization with classical networks' modularity.
  arXiv  Detail & Related papers  (2024-02-25T16:57:51Z)
• Mutual information maximizing quantum generative adversarial networks [9.391818870557545]
  InfoQGAN is a quantum-classical hybrid generative adversarial network that integrates the principles of InfoGAN with a QGAN architecture.<n>We show that InfoQGAN effectively mitigates mode collapse while achieving robust feature disentanglement in the quantum generator.<n>These results highlight the potential of InfoQGAN as an approach for advancing quantum generative modeling in the NISQ era.
  arXiv  Detail & Related papers  (2023-09-04T05:18:37Z)
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models [62.997667081978825]
  We build over a proposed framework for evaluating the generalization performance of generative models. We establish the first comparative race towards practical quantum advantage (PQA) between classical and quantum generative models. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models.
  arXiv  Detail & Related papers  (2023-03-27T22:48:28Z)
• Generalization Metrics for Practical Quantum Advantage in Generative Models [68.8204255655161]
  Generative modeling is a widely accepted natural use case for quantum computers. We construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Our simulation results show that our quantum-inspired models have up to a $68 times$ enhancement in generating unseen unique and valid samples.
  arXiv  Detail & Related papers  (2022-01-21T16:35:35Z)
• Generation of High-Resolution Handwritten Digits with an Ion-Trap Quantum Computer [55.41644538483948]
  We implement a quantum-circuit based generative model to learn and sample the prior distribution of a Generative Adversarial Network. We train this hybrid algorithm on an ion-trap device based on $171$Yb$+$ ion qubits to generate high-quality images.
  arXiv  Detail & Related papers  (2020-12-07T18:51:28Z)
• Experimental Quantum Generative Adversarial Networks for Image Generation [93.06926114985761]
  We experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor. Our work provides guidance for developing advanced quantum generative models on near-term quantum devices.
  arXiv  Detail & Related papers  (2020-10-13T06:57:17Z)

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.