Variational quantum generators: Generative adversarial quantum machine learning for continuous distributions

@article{Romero2019VariationalQG,
  title={Variational quantum generators: Generative adversarial quantum machine learning for continuous distributions},
  author={Jonathan Romero and Al{\'a}n Aspuru-Guzik},
  journal={arXiv: Quantum Physics},
  year={2019}
}
We propose a hybrid quantum-classical approach to model continuous classical probability distributions using a variational quantum circuit. The architecture of the variational circuit consists of two parts: a quantum circuit employed to encode a classical random variable into a quantum state, called the quantum encoder, and a variational circuit whose parameters are optimized to mimic a target probability distribution. Samples are generated by measuring the expectation values of a set of… Expand
43 Citations

Figures from this paper

Quantum Wasserstein Generative Adversarial Networks
  • 16
  • PDF
Quantum generative adversarial network for generating discrete distribution
  • 16
  • PDF
Experimental Quantum Generative Adversarial Networks for Image Generation
  • 10
  • PDF
Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications
  • 3
  • PDF
Addressing Temporal Variations in Qubit Quality Metrics for Parameterized Quantum Circuits
  • 5
  • PDF
Quantum-classical generative models for machine learning
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 109 REFERENCES
Differentiable Learning of Quantum Circuit Born Machine
  • 71
  • PDF
Quantum generative adversarial networks
  • 79
  • PDF
Quantum Generative Adversarial Learning.
  • 112
  • PDF
Barren plateaus in quantum neural network training landscapes
  • 213
  • PDF
Hierarchical quantum classifiers
  • 87
  • PDF
Quantum Circuit Learning
  • 224
  • PDF
...
1
2
3
4
5
...