Quantum Wasserstein Generative Adversarial Networks

Abstract

The study of quantum generative models is well-motivated, not only because of its importance in quantum machine learning and quantum chemistry but also because of the perspective of its implementation on near-term quantum machines. Inspired by previous studies on the adversarial training of classical and quantum generative models, we propose the first design of quantum Wasserstein Generative Adversarial Networks (WGANs), which has been shown to improve the robustness and the scalability of the adversarial training of quantum generative models even on noisy quantum hardware. Specifically, we propose a definition of the Wasserstein semimetric between quantum data, which inherits a few key theoretical merits of its classical counterpart. We also demonstrate how to turn the quantum Wasserstein semimetric into a concrete design of quantum WGANs that can be efficiently implemented on quantum machines. Our numerical study, via classical simulation of quantum systems, shows the more robust and scalable numerical performance of our quantum WGANs over other quantum GAN proposals. As a surprising application, our quantum WGAN has been used to generate a 3-qubit quantum circuit of ~50 gates that well approximates a 3-qubit 1-d Hamiltonian simulation circuit that requires over 10k gates using standard techniques.

Accepted to the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). Codes are available at https://github.com/yiminghwang/qWGAN

Cited by in corpus (20)

• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• On the Quantum versus Classical Learnability of Discrete Distributions
• QuGAN: A Quantum State Fidelity based Generative Adversarial Network
• Learning quantum data with the quantum Earth Mover's distance
• Quantum optimal transport with quantum channels
• Variational inference with a quantum computer
• Prospects and challenges of quantum finance
• Medical image classification via quantum neural networks
• Quantum semi-supervised generative adversarial network for enhanced data classification
• Quantum Monge-Kantorovich problem and transport distance between density matrices
• Quantum Capsule Networks
• Monotonicity of the quantum 2-Wasserstein distance
• Efficient option pricing with unary-based photonic computing chip and generative adversarial learning
• Quantum Expectation-Maximization for Gaussian Mixture Models
• Dynamical Mode Recognition of Coupled Flame Oscillators by Supervised and Unsupervised Learning Approaches
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Quantum Optimal Transport: Quantum Channels and Qubits
• Quantum statistical learning via Quantum Wasserstein natural gradient
• Energy risk analysis with Dynamic Amplitude Estimation and Piecewise Approximate Quantum Compiling