Operator Neural Jump ODEs: L squared-optimal prediction in function spaces
Florian Krach, Oliver Löthgren, Josef Teichmann
stat.ML, cs.LG
Submitted: 2026-07-25
Comments: 25 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Black box variational inference for state space models
- Layer Normalization
- Neural Jump ODEs as Generative Models
- Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
- Learning Chaotic Systems and Long-Term Predictions with Neural Jump ODEs
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- Deep Kalman Filters
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
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches