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

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 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.

References in corpus (23)

• Quantum Machine Learning
• Parameterized quantum circuits as machine learning models
• Defining and detecting quantum speedup
• Quantum machine learning: a classical perspective
• Average-case complexity versus approximate simulation of commuting quantum computations
• Quantum Adiabatic Markovian Master Equations
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Implementing a distance-based classifier with a quantum interference circuit
• Minor-embedding in adiabatic quantum computation: II. Minor-universal graph design
• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Quantum Sampling Problems, BosonSampling and Quantum Supremacy
• Quantum Variational Autoencoder
• Searching for quantum speedup in quasistatic quantum annealers
• Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers
• A NASA Perspective on Quantum Computing: Opportunities and Challenges
• Variational Quantum Boltzmann Machines
• Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
• Adversarial quantum circuit learning for pure state approximation
• Global warming: Temperature estimation in annealers
• Thermalization, freeze-out and noise: deciphering experimental quantum annealers
• Optimally Stopped Optimization
• Perils of Embedding for Sampling Problems
• Near-Term Quantum-Classical Associative Adversarial Networks

Cited by in corpus (12)

• Quantum Machine Learning: from physics to software engineering
• Variational inference with a quantum computer
• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Assessing and Advancing the Potential of Quantum Computing: A NASA Case Study
• Comparing the effects of Boltzmann machines as associative memory in Generative Adversarial Networks between classical and quantum sampling
• Preparing ground states of the XXZ model using the quantum annealing with inductively coupled superconducting flux qubits
• Physical Realization of Measurement Based Quantum Computation
• Solving systems of Boolean multivariate equations with quantum annealing
• Perils of Embedding for Quantum Sampling
• Quantum annealing with pairs of ${}^2\Sigma$ molecules as qubits
• Diabatic quantum annealing for training energy-based generative models
• Enhanced local addressability of a spin array with local exchange pulses and global microwave driving