A kernel-based regularizer derived from a GP prior on the Neural ODE vector field at finite points is added to the variational objective, paired with multiple shooting to handle long irregular trajectories.
Latent neural odes with sparse bayesian multiple shooting,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction
A kernel-based regularizer derived from a GP prior on the Neural ODE vector field at finite points is added to the variational objective, paired with multiple shooting to handle long irregular trajectories.