Physics-Informed Diffusion Models

arXiv:2403.14404v1 Announce Type: new
Abstract: Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied data distribution are expected to adhere to specific governing equations. We present a framework to inform denoising diffusion models on underlying constraints on such generated samples during model training. Our approach improves the alignment of the generated samples with the imposed constraints and …

abstract arxiv cs.ce cs.lg data denoising diffusion diffusion models distribution framework generative generative models machine machine learning physics physics-informed samples scientific type