L-DPS performs approximate Bayesian inference for PDE inverse problems by combining latent diffusion priors with surrogate-guided likelihood in a lower-dimensional space, demonstrated on Darcy flow permeability inversion.
Vae-dnn: Energy-efficient trainable-by-parts surrogate model for parametric partial differential equations.arXiv preprint arXiv:2508.03839, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems
L-DPS performs approximate Bayesian inference for PDE inverse problems by combining latent diffusion priors with surrogate-guided likelihood in a lower-dimensional space, demonstrated on Darcy flow permeability inversion.