A hybrid generative model combining an exit probability neural network with a training-free diffusion model learns stochastic flow maps for SDEs in bounded domains with absorbing boundaries.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative AI Models for Learning Flow Maps of Stochastic Dynamical Systems in Bounded Domains
A hybrid generative model combining an exit probability neural network with a training-free diffusion model learns stochastic flow maps for SDEs in bounded domains with absorbing boundaries.