DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912598811738112 |
|---|---|
| author | Zhang, Chi Zheng, Mengxin Lou, Qian Chen, Fan |
| author_facet | Zhang, Chi Zheng, Mengxin Lou, Qian Chen, Fan |
| contents | Variational Quantum Algorithms (VQAs) are widely used in the noisy intermediate-scale quantum (NISQ) era, but their trainability and performance depend critically on initialization parameters that shape the optimization landscape. Existing machine learning-based initializers achieve state-of-the-art results yet remain constrained to single-task domains and small datasets of only hundreds of samples. We address these limitations by reformulating VQA parameter initialization as a generative modeling problem and introducing DiffQ, a parameter initializer based on the Denoising Diffusion Probabilistic Model (DDPM). To support robust training and evaluation, we construct a dataset of 15,085 instances spanning three domains and five representative tasks. Experiments demonstrate that DiffQ surpasses baselines, reducing initial loss by up to 8.95 and convergence steps by up to 23.4%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17324 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models Zhang, Chi Zheng, Mengxin Lou, Qian Chen, Fan Emerging Technologies Machine Learning Quantum Physics Variational Quantum Algorithms (VQAs) are widely used in the noisy intermediate-scale quantum (NISQ) era, but their trainability and performance depend critically on initialization parameters that shape the optimization landscape. Existing machine learning-based initializers achieve state-of-the-art results yet remain constrained to single-task domains and small datasets of only hundreds of samples. We address these limitations by reformulating VQA parameter initialization as a generative modeling problem and introducing DiffQ, a parameter initializer based on the Denoising Diffusion Probabilistic Model (DDPM). To support robust training and evaluation, we construct a dataset of 15,085 instances spanning three domains and five representative tasks. Experiments demonstrate that DiffQ surpasses baselines, reducing initial loss by up to 8.95 and convergence steps by up to 23.4%. |
| title | DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models |
| topic | Emerging Technologies Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2509.17324 |