Quantum Generative Adversarial Network (QGAN) Benchmark

Benchmark for quantum generative adversarial networks that learn probability distributions and load them into quantum states. Through the interplay of quantum channels and classical neural networks, QGANs achieve polynomial gate complexity for distribution loading. Implementations on IBM Quantum hardware demonstrate competitive image generation on MNIST and Fashion-MNIST, with the MosaiQ framework achieving significant improvements in Frechet Inception Distance scores.[1]

  • Algorithm: Quantum Generative Adversarial Network (QGAN)
  • Category: machine-learning
  • Qubits: 8
  • Framework: Qiskit Machine Learning, PennyLane
  • Hardware: IBM Quantum, simulators
  • Reproducible: Yes
  • Published:
  • QGAN
  • generative-model
  • MNIST
  • machine-learning
  • distribution-learning

What algorithm does Quantum Generative Adversarial Network (QGAN) Benchmark use?

Quantum Generative Adversarial Network (QGAN) Benchmark uses the Quantum Generative Adversarial Network (QGAN) algorithm, categorized under machine-learning.

Frequently Asked Questions

What is the Quantum Generative Adversarial Network (QGAN) Benchmark benchmark?

Benchmark for quantum generative adversarial networks that learn probability distributions and load them into quantum states. Through the interplay of quantum channels and classical neural networks, QGANs achieve polynomial gate complexity for distribution loading. Implementations on IBM Quantum hardware demonstrate competitive image generation on MNIST and Fashion-MNIST, with the MosaiQ framework achieving significant improvements in Frechet Inception Distance scores.

Is Quantum Generative Adversarial Network (QGAN) Benchmark reproducible?

Yes, this benchmark is reproducible.

Sources

  1. "Quantum Generative Adversarial Networks for Learning and Loading Random Distributions", accessed 2026-03-19 — arXiv
  2. "Quantum Generative Adversarial Networks for learning and loading random distributions (npj Quantum Information)", accessed 2026-03-19 — DOI