Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning
This work addresses the challenge of leveraging quantum computing for machine learning, but it is incremental as it shows no performance advantage over classical methods in this specific application.
The researchers tackled the problem of integrating quantum annealing into deep learning by developing a quantum-assisted associative adversarial network, which uses a quantum annealer to sample from a graphical model in a GAN framework, and found that it achieved equivalent performance to classical methods on MNIST, with Fréchet inception distance and inception scores showing no significant difference.
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 Fréchet 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.