DeepAI AI Chat
Log In Sign Up

Quantum Wasserstein Generative Adversarial Networks

by   Shouvanik Chakrabarti, et al.

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.


page 1

page 2

page 3

page 4


Quantum generative adversarial networks

Quantum machine learning is expected to be one of the first potential ge...

Differentiable Learning of Quantum Circuit Born Machine

Quantum circuit Born machines are generative models which represent the ...

Learnability and Complexity of Quantum Samples

Given a quantum circuit, a quantum computer can sample the output distri...

Running the Dual-PQC GAN on noisy simulators and real quantum hardware

In an earlier work, we introduced dual-Parameterized Quantum Circuit (PQ...

Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy

The intrinsic probabilistic nature of quantum mechanics invokes endeavor...

Evaluating Generalization in Classical and Quantum Generative Models

Defining and accurately measuring generalization in generative models re...

Quantum Earth Mover's Distance: A New Approach to Learning Quantum Data

Quantifying how far the output of a learning algorithm is from its targe...

Code Repositories


The project codes associated with quantum Wasserstein GAN

view repo