Generative quantum advantage for classical and quantum problems

2025-09-10

AI Summary

Classical computers face fundamental limitations in learning intractable probability distributions and simulating quantum circuit dynamics. Method: We propose a novel trainable quantum generative model architecture specifically designed to mitigate gradient vanishing and local minima—key bottlenecks in quantum generative learning—and enable provably advantageous quantum sampling. Contribution/Results: Implemented on a 68-qubit superconducting quantum processor, our model successfully learns classically intractable distributions and accelerates quantum dynamical simulation beyond classical feasibility. This constitutes the first experimental demonstration of practical quantum advantage for generative modeling on intermediate-scale, noisy hardware. Crucially, the model achieves verifiable quantum supremacy in distribution learning and quantum circuit emulation, establishing a foundational milestone toward application-relevant quantum advantage in generative machine learning.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Recent breakthroughs in generative machine learning, powered by massive computational resources, have demonstrated unprecedented human-like capabilities. While beyond-classical quantum experiments can generate samples from classically intractable distributions, their complexity has thwarted all efforts toward efficient learning. This challenge has hindered demonstrations of generative quantum advantage: the ability of quantum computers to learn and generate desired outputs substantially better than classical computers. We resolve this challenge by introducing families of generative quantum models that are hard to simulate classically, are efficiently trainable, exhibit no barren plateaus or proliferating local minima, and can learn to generate distributions beyond the reach of classical computers. Using a $68$-qubit superconducting quantum processor, we demonstrate these capabilities in two scenarios: learning classically intractable probability distributions and learning quantum circuits for accelerated physical simulation. Our results establish that both learning and sampling can be performed efficiently in the beyond-classical regime, opening new possibilities for quantum-enhanced generative models with provable advantage.

Problem

• Demonstrating generative quantum advantage over classical computers
• Efficiently training quantum models without barren plateaus
• Learning classically intractable distributions using quantum processors

Innovation

• Efficiently trainable quantum generative models
• No barren plateaus or local minima
• Learning beyond-classical distributions efficiently