GAN generators can act as priors for Bayesian inference on high-dimensional fields with complex distributions, demonstrated on a heat conduction inverse problem.
Tarantola, Inverse problem theory and methods for model parameter estimation, volume 89, siam
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bayesian Inference with Generative Adversarial Network Priors
GAN generators can act as priors for Bayesian inference on high-dimensional fields with complex distributions, demonstrated on a heat conduction inverse problem.