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

arXiv: https://arxiv.org/abs/2601.05036 · HTML: https://mlsanity.com/paper/2601.05036/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Quantum generative adversarial networks](https://mlsanity.com/paper/1804.08641/) (2018)
- [Differentiable Learning of Quantum Circuit Born Machine](https://mlsanity.com/paper/1804.04168/) (2018)
- [Understanding quantum machine learning also requires rethinking generalization](https://mlsanity.com/paper/2306.13461/) (2023)
- [DeepSat - A Learning framework for Satellite Imagery](https://mlsanity.com/paper/1509.03602/) (2015)
- [Quantum Generative Models for Small Molecule Drug Discovery](https://mlsanity.com/paper/2101.03438/) (2021)
- [Quantum Convolutional Neural Networks are Effectively Classically Simulable](https://mlsanity.com/paper/2408.12739/) (2024)
- [From GAN to WGAN](https://mlsanity.com/paper/1904.08994/) (2019)
- [A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation](https://mlsanity.com/paper/2402.08703/) (2024)
- [A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis](https://mlsanity.com/paper/2201.07646/) (2022)
- [Let Quantum Neural Networks Choose Their Own Frequencies](https://mlsanity.com/paper/2309.03279/) (2023)
- [Style-based quantum generative adversarial networks for Monte Carlo events](https://mlsanity.com/paper/2110.06933/) (2021)
- [Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric](https://mlsanity.com/paper/2303.13462/) (2023)
- [Hybrid quantum cycle generative adversarial network for small molecule generation](https://mlsanity.com/paper/2402.00014/) (2023)
- [Expressive equivalence of classical and quantum restricted Boltzmann machines](https://mlsanity.com/paper/2502.17562/) (2025)
- [Spectral Bias in Variational Quantum Machine Learning](https://mlsanity.com/paper/2506.22555/) (2025)
- [DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification](https://mlsanity.com/paper/1911.07747/) (2019)

## Built on by (most cited first, 2 of 2)

- [Learning Quantum Data Distribution via Chaotic Quantum Diffusion Model](https://mlsanity.com/paper/2602.22061/) (2026)
- [Latent Style-based Quantum Wasserstein GAN for Drug Design](https://mlsanity.com/paper/2603.22399/) (2026)

## Abstract (arXiv)

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.