Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912599146233856 |
|---|---|
| author | Quinn, Daniel Buffoni, Lorenzo Gherardini, Stefano De Chiara, Gabriele |
| author_facet | Quinn, Daniel Buffoni, Lorenzo Gherardini, Stefano De Chiara, Gabriele |
| contents | Quantum denoising diffusion models have recently emerged as a powerful framework for generative quantum machine learning. In this work, we extend these models by introducing a conditioning mechanism that enables the generation of quantum states drawn from multiple target distributions. By sharing parameters across distinct classes of quantum states, our approach avoids the need to train separate models for each distribution. We validate our method through numerical simulations that span single-qubit generation tasks, entangled state preparation, and many-body ground state generation. Across these tasks, conditioning significantly reduced the error of targeted state generation by up to an order of magnitude. Finally, we perform an ablation study to quantify the effect of key hyperparameters on the model performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Conditioning in Generative Quantum Denoising Diffusion Models Quinn, Daniel Buffoni, Lorenzo Gherardini, Stefano De Chiara, Gabriele Quantum Physics Quantum denoising diffusion models have recently emerged as a powerful framework for generative quantum machine learning. In this work, we extend these models by introducing a conditioning mechanism that enables the generation of quantum states drawn from multiple target distributions. By sharing parameters across distinct classes of quantum states, our approach avoids the need to train separate models for each distribution. We validate our method through numerical simulations that span single-qubit generation tasks, entangled state preparation, and many-body ground state generation. Across these tasks, conditioning significantly reduced the error of targeted state generation by up to an order of magnitude. Finally, we perform an ablation study to quantify the effect of key hyperparameters on the model performance. |
| title | Conditioning in Generative Quantum Denoising Diffusion Models |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2509.17569 |