Improving GANs by leveraging the quantum noise from real hardware

• URL: http://arxiv.org/abs/2507.01886v1
• Date: Wed, 02 Jul 2025 16:56:09 GMT
• Title: Improving GANs by leveraging the quantum noise from real hardware
• Authors: Hongni Jin, Kenneth M. Merz Jr,
• Abstract summary: We propose a novel approach to generative adversarial networks (GANs) in which the standard i.i.d. Gaussian latent prior is replaced or hybridized with a quantum-correlated prior.<n>We show that intrinsic quantum randomness and device-specific imperfections can provide a structured inductive bias that enhances GAN performance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel approach to generative adversarial networks (GANs) in which the standard i.i.d. Gaussian latent prior is replaced or hybridized with a quantum-correlated prior derived from measurements of a 16-qubit entangling circuit. Each latent sample is generated by grouping repeated shots per qubit into a binary fraction, applying the inverse Gaussian CDF to obtain a 16-dimensional Gaussian vector whose joint copula reflects genuine quantum entanglement, and then projecting into the high-dimensional space via a fixed random matrix. By pre-sampling tens of millions of bitstrings, either from a noiseless simulator or from IBM hardware, we build large pools of independent but internally quantum-correlated latents. We integrate this prior into three representative architectures (WGAN, SNGAN, BigGAN) on CIFAR-10, making no changes to the neural network structure or training hyperparameters. The hybrid latent representations incorporating hardware-derived noise consistently lower the FID relative to both the classical baseline and the simulator variant, especially when the quantum component constitutes a substantial fraction of the prior. In addition, we execute on the QPU in parallel to not only save computing time but also further decrease the FID up to 17% in BigGAN. These results indicate that intrinsic quantum randomness and device-specific imperfections can provide a structured inductive bias that enhances GAN performance. Our work demonstrates a practical pipeline for leveraging noisy quantum hardware to enrich deep-generative modeling, opening a new interface between quantum information and machine learning. All code and data are available at https://github.com/Neon8988/GAN_QN.git.

Related papers

• Unitary Scrambling and Collapse: A Quantum Diffusion Framework for Generative Modeling [5.258882634977828]
  We propose QSC-Diffusion, the first fully quantum diffusion-based framework for image generation.<n>We employ parameterized quantum circuits with measurement-induced collapse for reverse denoising.<n>Remarkably, QSC-Diffusion achieves competitive FID scores across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-12T11:00:21Z)
• Evaluating the performance of quantum processing units at large width and depth [0.40964539027092917]
  We introduce a benchmarking protocol based on the linear ramp quantum approximate optimization algorithm (LR-QAOA)<n>LR-QAOA quantifies a QPU's ability to preserve a coherent signal as circuit depth increases, identifying when performance becomes statistically indistinguishable from random sampling.<n>We apply this protocol to 24 quantum processors from six vendors, testing problems with up to 156 qubits and 10,000 layers across 1D-chains, native layouts, and fully connected topologies.
  arXiv  Detail & Related papers  (2025-02-10T13:50:50Z)
• GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching [43.496857395654764]
  We explore the potential of leveraging Large Language Models to simulate the output of a quantum Turing machine.<n>A specialized model, GroverGPT, trained on over 15 trillion tokens.<n>It consistently outperformed OpenAI's GPT-4o (45% accuracy), achieving nearly 100% accuracy on 6- and 10-qubit datasets.<n>It also demonstrated strong generalization, surpassing 95% accuracy for systems with over 20 qubits when trained on 3- to 6-qubit data.
  arXiv  Detail & Related papers  (2024-12-30T20:23:10Z)
• QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits [82.50620782471485]
  QuantumSEA is an in-time sparse exploration for noise-adaptive quantum circuits. It aims to achieve two key objectives: (1) implicit circuits capacity during training and (2) noise robustness. Our method establishes state-of-the-art results with only half the number of quantum gates and 2x time saving of circuit executions.
  arXiv  Detail & Related papers  (2024-01-10T22:33:00Z)
• A Hybrid Quantum-Classical Generative Adversarial Network for Near-Term Quantum Processors [0.0]
  We present a hybrid quantum-classical generative adversarial network (GAN) for near-term quantum processors. The generator network is realized using an angle encoding quantum circuit and a variational quantum ansatz. The discriminator network is realized using multi-stage trainable encoding quantum circuits.
  arXiv  Detail & Related papers  (2023-07-06T20:11:28Z)
• Simulation of Entanglement Generation between Absorptive Quantum Memories [56.24769206561207]
  We use the open-source Simulator of QUantum Network Communication (SeQUeNCe), developed by our team, to simulate entanglement generation between two atomic frequency comb (AFC) absorptive quantum memories. We realize the representation of photonic quantum states within truncated Fock spaces in SeQUeNCe. We observe varying fidelity with SPDC source mean photon number, and varying entanglement generation rate with both mean photon number and memory mode number.
  arXiv  Detail & Related papers  (2022-12-17T05:51:17Z)
• TopGen: Topology-Aware Bottom-Up Generator for Variational Quantum Circuits [26.735857677349628]
  Variational Quantum Algorithms (VQA) are promising to demonstrate quantum advantages on near-term devices. Designing ansatz, a variational circuit with parameterized gates, is of paramount importance for VQA. We propose a bottom-up approach to generate topology-specific ansatz.
  arXiv  Detail & Related papers  (2022-10-15T04:18:41Z)
• Entangling Quantum Generative Adversarial Networks [53.25397072813582]
  We propose a new type of architecture for quantum generative adversarial networks (entangling quantum GAN, EQ-GAN) We show that EQ-GAN has additional robustness against coherent errors and demonstrate the effectiveness of EQ-GAN experimentally in a Google Sycamore superconducting quantum processor.
  arXiv  Detail & Related papers  (2021-04-30T20:38:41Z)
• Tensor Network Quantum Virtual Machine for Simulating Quantum Circuits at Exascale [57.84751206630535]
  We present a modernized version of the Quantum Virtual Machine (TNQVM) which serves as a quantum circuit simulation backend in the e-scale ACCelerator (XACC) framework. The new version is based on the general purpose, scalable network processing library, ExaTN, and provides multiple quantum circuit simulators. By combining the portable XACC quantum processors and the scalable ExaTN backend we introduce an end-to-end virtual development environment which can scale from laptops to future exascale platforms.
  arXiv  Detail & Related papers  (2021-04-21T13:26:42Z)
• 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)
• QuGAN: A Quantum State Fidelity based Generative Adversarial Network [10.110634675568203]
  Generative Adversarial Network (GAN) has been widely used for generating artificial images, text-to-image or image augmentation across areas of science, arts and video games. We propose QuGAN, a quantum GAN architecture that provides stable convergence, quantum-state based gradients and significantly reduced parameter sets.
  arXiv  Detail & Related papers  (2020-10-18T17:10:07Z)

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.