System-Embedded Diffusion Bridge Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909868181422080 |
|---|---|
| author | Sobieski, Bartlomiej Tivnan, Matthew Wang, Yuang Yoon, Siyeop Jin, Pengfei Wu, Dufan Li, Quanzheng Biecek, Przemyslaw |
| author_facet | Sobieski, Bartlomiej Tivnan, Matthew Wang, Yuang Yoon, Siyeop Jin, Pengfei Wu, Dufan Li, Quanzheng Biecek, Przemyslaw |
| contents | Solving inverse problems -- recovering signals from incomplete or noisy measurements -- is fundamental in science and engineering. Score-based generative models (SGMs) have recently emerged as a powerful framework for this task. Two main paradigms have formed: unsupervised approaches that adapt pretrained generative models to inverse problems, and supervised bridge methods that train stochastic processes conditioned on paired clean and corrupted data. While the former typically assume knowledge of the measurement model, the latter have largely overlooked this structural information. We introduce System embedded Diffusion Bridge Models (SDBs), a new class of supervised bridge methods that explicitly embed the known linear measurement system into the coefficients of a matrix-valued SDE. This principled integration yields consistent improvements across diverse linear inverse problems and demonstrates robust generalization under system misspecification between training and deployment, offering a promising solution to real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23726 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | System-Embedded Diffusion Bridge Models Sobieski, Bartlomiej Tivnan, Matthew Wang, Yuang Yoon, Siyeop Jin, Pengfei Wu, Dufan Li, Quanzheng Biecek, Przemyslaw Machine Learning Artificial Intelligence Solving inverse problems -- recovering signals from incomplete or noisy measurements -- is fundamental in science and engineering. Score-based generative models (SGMs) have recently emerged as a powerful framework for this task. Two main paradigms have formed: unsupervised approaches that adapt pretrained generative models to inverse problems, and supervised bridge methods that train stochastic processes conditioned on paired clean and corrupted data. While the former typically assume knowledge of the measurement model, the latter have largely overlooked this structural information. We introduce System embedded Diffusion Bridge Models (SDBs), a new class of supervised bridge methods that explicitly embed the known linear measurement system into the coefficients of a matrix-valued SDE. This principled integration yields consistent improvements across diverse linear inverse problems and demonstrates robust generalization under system misspecification between training and deployment, offering a promising solution to real-world applications. |
| title | System-Embedded Diffusion Bridge Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.23726 |