# Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning

## TL;DR

This paper introduces a quantum-assisted generative adversarial network that leverages quantum annealing to improve learning of latent variable models, demonstrating comparable performance to classical methods on image datasets.

## Contribution

The paper presents a novel quantum-assisted GAN framework using quantum annealing for sampling, enabling testing of quantum advantages in deep learning models.

## Key findings

- Quantum-assisted GAN successfully learns MNIST dataset.
- Quantum and classical methods show similar performance on MNIST.
- Applied to LSUN bedrooms dataset with promising results.

## Abstract

We present an algorithm for learning a latent variable generative model via generative adversarial learning where the canonical uniform noise input is replaced by samples from a graphical model. This graphical model is learned by a Boltzmann machine which learns low-dimensional feature representation of data extracted by the discriminator. A quantum annealer, the D-Wave 2000Q, is used to sample from this model. This algorithm joins a growing family of algorithms that use a quantum annealing subroutine in deep learning, and provides a framework to test the advantages of quantum-assisted learning in GANs. Fully connected, symmetric bipartite and Chimera graph topologies are compared on a reduced stochastically binarized MNIST dataset, for both classical and quantum annealing sampling methods. The quantum-assisted associative adversarial network successfully learns a generative model of the MNIST dataset for all topologies, and is also applied to the LSUN dataset bedrooms class for the Chimera topology. Evaluated using the Fr\'{e}chet inception distance and inception score, the quantum and classical versions of the algorithm are found to have equivalent performance for learning an implicit generative model of the MNIST dataset.