A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models

Abstract

Generative modeling has seen a rising interest in both classical and quantum machine learning, and it represents a promising candidate to obtain a practical quantum advantage in the near term. In this study, we build over a proposed framework for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). After defining four types of PQAs scenarios, we focus on what we refer to as potential PQA, aiming to compare quantum models with the best-known classical algorithms for the task at hand. We let the models race on a well-defined and application-relevant competition setting, where we illustrate and demonstrate our framework on 20 variables (qubits) generative modeling task. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models. Such a feature is highly desirable in a wide range of real-world applications where the available data is scarce.

arXiv comment17 pages, 5 figures, 3 tables

References in corpus (20)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Training language models to follow instructions with human feedback
• Supervised learning with quantum enhanced feature spaces
• Quantum Convolutional Neural Networks
• Characterizing Quantum Supremacy in Near-Term Devices
• Defining and detecting quantum speedup
• Quantum advantage in learning from experiments
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum Boltzmann Machine
• Quantum Supremacy and the Complexity of Random Circuit Sampling
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• On the Quantum versus Classical Learnability of Discrete Distributions
• Bias and Generalization in Deep Generative Models: An Empirical Study
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• U(1) symmetric recurrent neural networks for quantum state reconstruction
• Quantum utility -- definition and assessment of a practical quantum advantage
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization

Cited by in corpus (11)

• Quantum Cloud Computing: Trends and Challenges
• Integrating Quantum Computing Resources into Scientific HPC Ecosystems
• Quantum-Noise-Driven Generative Diffusion Models
• Simulating unsteady fluid flows on a superconducting quantum processor
• How quantum computing can enhance biomarker discovery
• Protocols for Trainable and Differentiable Quantum Generative Modelling
• A quantum computing concept for 1-D elastic wave simulation with exponential speedup
• Tensor tree learns hidden relational structures in data to construct generative models
• Quantum-Enhanced Generative Models for Rare Event Prediction
• Quantum Chebyshev Probabilistic Models for Fragmentation Functions
• Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems