Protocols for Trainable and Differentiable Quantum Generative Modelling

Abstract

We propose an approach for learning probability distributions as differentiable quantum circuits (DQC) that enable efficient quantum generative modelling (QGM) and synthetic data generation. Contrary to existing QGM approaches, we perform training of a DQC-based model, where data is encoded in a latent space with a phase feature map, followed by a variational quantum circuit. We then map the trained model to the bit basis using a fixed unitary transformation, coinciding with a quantum Fourier transform circuit in the simplest case. This allows fast sampling from parametrized distributions using a single-shot readout. Importantly, simplified latent space training provides models that are automatically differentiable, and we show how samples from distributions propagated by stochastic differential equations (SDEs) can be accessed by solving stationary and time-dependent Fokker-Planck equations with a quantum protocol. Finally, our approach opens a route to multidimensional generative modelling with qubit registers explicitly correlated via a (fixed) entangling layer. In this case quantum computers can offer advantage as efficient samplers, which perform complex inverse transform sampling enabled by the fundamental laws of quantum mechanics. On a technical side the advances are multiple, as we introduce the phase feature map, analyze its properties, and develop frequency-taming techniques that include qubit-wise training and feature map sparsification.

16 pages, 9 figures; first version, to be updated soon

References in corpus (16)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum computational advantage using photons
• Strong quantum computational advantage using a superconducting quantum processor
• Quantum advantage in learning from experiments
• Theory of overparametrization in quantum neural networks
• On the practical usefulness of the Hardware Efficient Ansatz
• Evolutional Deep Neural Network
• Generalized quantum circuit differentiation rules
• Generative Quantum Learning of Joint Probability Distribution Functions
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models
• A variational quantum algorithm for the Feynman-Kac formula
• Dual-Parameterized Quantum Circuit GAN Model in High Energy Physics
• Quantum Fourier analysis for multivariate functions and applications to a class of Schrödinger-type partial differential equations
• Efficient Bipartite Entanglement Detection Scheme with a Quantum Adversarial Solver
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits

Cited by in corpus (7)

• Ground state-based quantum feature maps
• Multidimensional Quantum Generative Modeling by Quantum Hartley Transform
• LArTPC hit-based topology classification with quantum machine learning and symmetry
• Vortex Detection from Quantum Data
• Quantum community detection via deterministic elimination
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions
• Quantum-assisted tracer dispersion in turbulent shear flow