A purely Quantum Generative Modeling through Unitary Scrambling and Collapse

Yihua Li, Jiayi Chen, Tamanna Surendar Kumavat, Kyriakos FlourisOpenReview 2026 · Submission to ICLR 2026 · Rejected · OpenReview

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 \ac{qsc}, a purely quantum paradigm that eliminates classical architectural 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.
BibTeX
@misc{li2026purely,
  author = {Yihua Li and Jiayi Chen and Tamanna Surendar Kumavat and Kyriakos Flouris},
  title = {{A purely Quantum Generative Modeling through Unitary Scrambling and Collapse}},
  year = {2026},
  url = {https://openreview.net/forum?id=wJTD7wQh40},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}
Figure