Constrained Synthesis with Projected Diffusion Models

Abstract

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.

Cite

Text

Christopher et al. "Constrained Synthesis with Projected Diffusion Models." Neural Information Processing Systems, 2024. doi:10.52202/079017-2834

Markdown

[Christopher et al. "Constrained Synthesis with Projected Diffusion Models." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/christopher2024neurips-constrained/) doi:10.52202/079017-2834

BibTeX

@inproceedings{christopher2024neurips-constrained,
  title     = {{Constrained Synthesis with Projected Diffusion Models}},
  author    = {Christopher, Jacob K. and Baek, Stephen and Fioretto, Ferdinando},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-2834},
  url       = {https://mlanthology.org/neurips/2024/christopher2024neurips-constrained/}
}