Score Matching via Differentiable Physics

Benjamin Holzschuh, Simona Vegetti, Nils ThuereyICLR 2023 · OpenReview

Abstract

Diffusion models based on stochastic differential equations (SDEs) gradually perturb a data distribution $p(\mathbf{x})$ over time by adding noise to it. A neural network is trained to approximate the score $\nabla_\mathbf{x} \log p_t(\mathbf{x})$ at time $t$, which can be used to reverse the corruption process. In this paper, we focus on learning the score field that is associated with the time evolution according to a physics operator in the presence of natural non-deterministic physical processes like diffusion. A decisive difference to previous methods is that the SDE underlying our approach transforms the state of a physical system to another state at a later time. For that purpose, we replace the drift of the underlying SDE formulation with a differentiable simulator or a neural network approximation of the physics. At the core of our method, we optimize the so-called probability flow ODE to fit a training set of simulation trajectories inside an ODE solver and solve the reverse-time SDE for inference to sample plausible trajectories that evolve towards a given end state. We demonstrate the competitiveness of our approach for different challenging inverse problems.
BibTeX
@inproceedings{holzschuh2023score,
  author = {Benjamin Holzschuh and Simona Vegetti and Nils Thuerey},
  title = {{Score Matching via Differentiable Physics}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=t9myAV_dpCB},
}

Loading related content...

Figure