Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2605.01122 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915973919932416 |
|---|---|
| author | Zheng, Bowen Kamdin, Katayun Shapiro, David Ditter, Alexander Sasaki, Dayne Bernard, Emma Kukreja, Roopali Zwart, Petrus H. Nemšák, Slavomír Mehta, Apurva Schwarz, Nicholas Hexemer, Alexander Chavez, Tanny |
| author_facet | Zheng, Bowen Kamdin, Katayun Shapiro, David Ditter, Alexander Sasaki, Dayne Bernard, Emma Kukreja, Roopali Zwart, Petrus H. Nemšák, Slavomír Mehta, Apurva Schwarz, Nicholas Hexemer, Alexander Chavez, Tanny |
| contents | Iterative ptychographic reconstruction algorithms are widely used for coherent diffractive imaging but can exhibit slow convergence under realistic experimental conditions. We propose a machine learning-augmented approach that accelerates iterative ptychographic reconstruction by introducing a learned fast-forward operator applied during reconstruction. Following an initial warm-up using standard iterations, the fast-forward operator advances the reconstruction toward a more converged state, after which conventional iterative updates are resumed. This strategy preserves the physical consistency and flexibility of established ptychographic solvers while reducing the number of iterations required for convergence. The model is trained on diverse ptychographic datasets and evaluated on experimental data acquired in a different year, demonstrating robustness and temporal generalization. Compared with conventional iterative solvers, the machine learning-augmented method achieves comparable reconstruction quality while converging faster in terms of Poisson negative log-likelihood, yielding over a two-fold reduction in wall-clock time. The approach has been integrated into an existing reconstruction pipeline and deployed in production at a synchrotron beamline, demonstrating practicality for real-time experimental operation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01122 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine Learning-Augmented Acceleration of Iterative Ptychographic Reconstruction Zheng, Bowen Kamdin, Katayun Shapiro, David Ditter, Alexander Sasaki, Dayne Bernard, Emma Kukreja, Roopali Zwart, Petrus H. Nemšák, Slavomír Mehta, Apurva Schwarz, Nicholas Hexemer, Alexander Chavez, Tanny Machine Learning Optics Iterative ptychographic reconstruction algorithms are widely used for coherent diffractive imaging but can exhibit slow convergence under realistic experimental conditions. We propose a machine learning-augmented approach that accelerates iterative ptychographic reconstruction by introducing a learned fast-forward operator applied during reconstruction. Following an initial warm-up using standard iterations, the fast-forward operator advances the reconstruction toward a more converged state, after which conventional iterative updates are resumed. This strategy preserves the physical consistency and flexibility of established ptychographic solvers while reducing the number of iterations required for convergence. The model is trained on diverse ptychographic datasets and evaluated on experimental data acquired in a different year, demonstrating robustness and temporal generalization. Compared with conventional iterative solvers, the machine learning-augmented method achieves comparable reconstruction quality while converging faster in terms of Poisson negative log-likelihood, yielding over a two-fold reduction in wall-clock time. The approach has been integrated into an existing reconstruction pipeline and deployed in production at a synchrotron beamline, demonstrating practicality for real-time experimental operation. |
| title | Machine Learning-Augmented Acceleration of Iterative Ptychographic Reconstruction |
| topic | Machine Learning Optics |
| url | https://arxiv.org/abs/2605.01122 |