
Drifting Fields are not Conservative
Drift fields in generative models are generally non-conservative; sharp normalization makes them gradients of a scalar potential, bridging to Wasserstein gradient flows and denoising score matching.

Drift fields in generative models are generally non-conservative; sharp normalization makes them gradients of a scalar potential, bridging to Wasserstein gradient flows and denoising score matching.

Fast probabilistic counterparts to numerical PDE solvers, powered by SPDEs & sparse linear algebra.

Introduces GP-FVM, a probabilistic counterpart to the finite volume method, enabling large-scale probabilistic PDE simulations.