Timezone: »

 
Score Matching via Differentiable Physics
Benjamin Holzschuh · Simona Vegetti · Nils Thuerey

@
in Machine Learning and the Physical Sciences »
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.
[ Poster] 

Author Information

Benjamin Holzschuh (Technical University Munich, Max-Planck Institute for Astrophysics)
Simona Vegetti (Max Planck Institute for Astrophysics)
Nils Thuerey (Technical University of Munich)

More from the Same Authors