Research map / Time series / Causal and generative time series
Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use NJ-ODE instead of GRU-ODE-Bayes | Black-Scholes · Black-Scholes | evaluation metric (min): 7 \cdot 10^{-4} -> 7 \cdot 10^{-4} | No clear effect |
| Use NJ-ODE instead of GRU-ODE-Bayes | Ornstein-Uhlenbeck · Ornstein-Uhlenbeck | evaluation metric (min): 3 \cdot 10^{-5} -> 5 \cdot 10^{-4} | Hurt |
| Use NJ-ODE instead of GRU-ODE-Bayes | Heston · Heston | evaluation metric (min): 4.24 -> 1.33 | Helped |
| Use NJ-ODE (small) instead of GRU-ODE-Bayes | USHCN · USHCN test | MSE: 0.43 \pm 0.07 -> 0.45 \pm 0.06 | Hurt |
| Use NJ-ODE (large) instead of GRU-ODE-Bayes | USHCN · USHCN test | MSE: 0.43 \pm 0.07 -> 0.40 $\pm$ 0.07 | Helped |
| Use NJ-ODE instead of Latent ODE + Poisson | PhysioNet Challenge 2012 extrapolation · PhysioNet Challenge 2012 test | MSE (× 10^-3): 2.208 \pm 0.050 -> 1.945 $\pm$ 0.007 | Helped |
Closest papers by meaning
- Neural Jump Stochastic Differential Equations (NeurIPS 2019 · similarity 0.90)
- Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction (NeurIPS 2025 · similarity 0.89)
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data (ICLR 2024 · similarity 0.89)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.89)
- Global Convergence in Neural ODEs: Impact of Activation Functions (ICLR 2025 · similarity 0.87)
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.