A purely Quantum Generative Modeling through Unitary Scrambling and Collapse

TL;DR

This paper introduces QGen, a fully quantum generative model that uses unitary scrambling and collapse processes, avoiding classical components, and demonstrates promising results for near-term quantum hardware.

Contribution

QGen is a novel purely quantum generative model that employs coherent scrambling and collapse processes, with a scalable measurement-based training method.

Findings

QGen outperforms classical and hybrid models with similar parameters.

QGen maintains robustness under finite-shot sampling.

QGen shows strong feasibility for near-term quantum hardware.

Abstract

Quantum computing offers fundamentally more expressive mechanisms for generative modeling, yet current approaches remain constrained by classical neural components that bottleneck quantum capability and hardware efficiency. We propose the Quantum Scrambling and Collapse Generative Model (QGen), a purely quantum paradigm that eliminates classical dependencies. QGen implements two coherent processes: scrambling, which interleaves Gaussian diffusion channels with unitary delocalization to disperse information globally while avoiding collapse into uninformative states; and collapse, where parameterized quantum circuits refocus scrambled distributions into structured outputs, achieving distributional reconstruction under coherent evolution. To enable scalability, we introduce a measurement-based training principle that decomposes learning into tractable subproblems, mitigating barren plateaus. Empirically, QGen outperforms classical and hybrid baselines under matched parameter budget, while maintaining robustness under finite-shot sampling, demonstrating strong feasibility for near-term hardware.