Gaussian Flow Dynamics: Simulation-Free Neural SDE Learning Beyond One-Time Marginals
stat.ML, cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- The general mixture-diffusion SDE and its relationship with an uncertain-volatility option model with volatility-asset decorrelation
- Stochastic Normalizing Flows
- Closing the Approximation Gap in Simulation-free Latent SDEs
- Improving Variational Auto-Encoders using Householder Flow
- Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier