A learned-score Langevin hypernetwork approximates the posterior over neural ODE weights, giving uncertainty estimates for history-dependent physical models.
Observers for multivariable systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Uncertainty quantification of neural network models of evolving processes via Langevin sampling
A learned-score Langevin hypernetwork approximates the posterior over neural ODE weights, giving uncertainty estimates for history-dependent physical models.