A performance characterization of quantum generative models

Abstract

Quantum generative modeling is a growing area of interest for industry-relevant applications. With the field still in its infancy, there are many competing techniques. This work is an attempt to systematically compare a broad range of these techniques to guide quantum computing practitioners when deciding which models and techniques to use in their applications. We compare fundamentally different architectural ansatzes of parametric quantum circuits used for quantum generative modeling: 1. A continuous architecture, which produces continuous-valued data samples, and 2. a discrete architecture, which samples on a discrete grid. We compare the performance of different data transformations: normalization by the min-max transform or by the probability integral transform. We learn the underlying probability distribution of the data sets via two popular training methods: 1. quantum circuit Born machines (QCBM), and 2. quantum generative adversarial networks (QGAN). We study their performance and trade-offs as the number of model parameters increases, with the baseline of similarly trained classical neural networks. The study is performed on six low-dimensional synthetic and two real financial data sets. Our two key findings are that: 1. For all data sets, our quantum models require similar or fewer parameters than their classical counterparts. In the extreme case, the quantum models require two of orders of magnitude less parameters. 2. We empirically find that a variant of the discrete architecture, which learns the copula of the probability distribution, outperforms all other methods.

arXiv commentRevised version: Small corrections to figures, additional references, and link to open-source code associated with the project. This version is in line with the version accepted for publication

References in corpus (37)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Generative Adversarial Networks: An Overview
• Quantum Circuit Learning
• An introduction to quantum machine learning
• Parameterized quantum circuits as machine learning models
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Data re-uploading for a universal quantum classifier
• Quantum generative adversarial networks
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Transfer learning in hybrid classical-quantum neural networks
• A generative modeling approach for benchmarking and training shallow quantum circuits
• The Expressive Power of Parameterized Quantum Circuits
• Quantum Risk Analysis
• Differentiable Learning of Quantum Circuit Born Machine
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Quantum generative adversarial network for generating discrete distribution
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Establishing the Quantum Supremacy Frontier with a 281 Pflop/s Simulation
• Approximate amplitude encoding in shallow parameterized quantum circuits and its application to financial market indicator
• Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
• Learning and Inference on Generative Adversarial Quantum Circuits
• On the Quantum versus Classical Learnability of Discrete Distributions
• Enhancing Generative Models via Quantum Correlations
• Fast quantum circuit cutting with randomized measurements
• QuGAN: A Quantum State Fidelity based Generative Adversarial Network
• Generative model benchmarks for superconducting qubits
• Variational inference with a quantum computer
• Style-based quantum generative adversarial networks for Monte Carlo events
• Generative Quantum Learning of Joint Probability Distribution Functions
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• Impact of quantum noise on the training of quantum Generative Adversarial Networks
• Shape-Guided Diffusion with Inside-Outside Attention
• Running the Dual-PQC GAN on noisy simulators and real quantum hardware

Cited by in corpus (4)

• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Benchmarking Quantum Generative Learning: A Study on Scalability and Noise Resilience using QUARK
• Quantum-Enhanced Generative Models for Rare Event Prediction
• Variational Quantum Generative Modeling by Sampling Expectation Values of Tunable Observables