Efficient, multimodal, and derivative-free bayesian inference with Fisher–Rao gradient flows
In this paper, we study efficient approximate sampling for probability distributions known up
to normalization constants. We specifically focus on a problem class arising in Bayesian …
to normalization constants. We specifically focus on a problem class arising in Bayesian …
Neural Galerkin schemes for sequential-in-time solving of partial differential equations with deep networks
J Berman, P Schwerdtner… - … Analysis Meets Machine …, 2024 - nyuscholars.nyu.edu
Abstract This survey discusses Neural Galerkin schemes that leverage nonlinear
parametrizations such as deep networks to numerically solve time-dependent partial …
parametrizations such as deep networks to numerically solve time-dependent partial …