Constrained Synthesis with Projected Diffusion Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909374838996992 |
|---|---|
| author | Christopher, Jacob K Baek, Stephen Fioretto, Ferdinando |
| author_facet | Christopher, Jacob K Baek, Stephen Fioretto, Ferdinando |
| contents | This paper introduces an approach to endow generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional sampling process of generative diffusion models as a constrained optimization problem, steering the generated data distribution to remain within a specified region to ensure adherence to the given constraints. These capabilities are validated on applications featuring both convex and challenging, non-convex, constraints as well as ordinary differential equations, in domains spanning from synthesizing new materials with precise morphometric properties, generating physics-informed motion, optimizing paths in planning scenarios, and human motion synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03559 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Constrained Synthesis with Projected Diffusion Models Christopher, Jacob K Baek, Stephen Fioretto, Ferdinando Machine Learning Artificial Intelligence This paper introduces an approach to endow generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional sampling process of generative diffusion models as a constrained optimization problem, steering the generated data distribution to remain within a specified region to ensure adherence to the given constraints. These capabilities are validated on applications featuring both convex and challenging, non-convex, constraints as well as ordinary differential equations, in domains spanning from synthesizing new materials with precise morphometric properties, generating physics-informed motion, optimizing paths in planning scenarios, and human motion synthesis. |
| title | Constrained Synthesis with Projected Diffusion Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.03559 |