Research map / Time series / Causal and generative time series
Random Controlled Differential Equations
Francesco Piatti, Thomas Cass, William F. Turner
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add random Fourier feature lift before the CDE dynamics (RF-CDE vs R-CDE) | R-CDE · UEA (16 datasets, N=250) | average accuracy: 0.695 -> 0.741 | Improved |
| use log-signature rough-path inputs (R-RDE vs R-CDE) | R-CDE · UEA (16 datasets, N=250) | average accuracy: 0.695 -> 0.708 | Improved |
| use RF-CDE instead of kernel SigPDE | SigPDE · UEA (16 datasets, N=250) | average accuracy: 0.738 -> 0.741 | No clear effect |
| use RF-CDE instead of RFSF variants | RFSF-DP · UEA (16 datasets, N=250) | average accuracy: 0.726 -> 0.741 | Improved |
| use R-RDE instead of R-CDE on rough fBm | R-CDE · Hurst V2, N=64 | accuracy: 0.635 -> 0.735 | Improved |
| use R-RDE instead of RFSF-TRP on rough fBm | RFSF-TRP · Hurst V2, N=100 | accuracy: 0.675 -> 0.730 | Improved |
| use R-RDE instead of Neural RDE | NRDE · Hurst V2, N=64 | accuracy: 0.675 -> 0.735 | Improved |
| use R-RDE instead of RF-CDE on raw fBm | RF-CDE · Hurst V1, N=100 | accuracy: 0.945 -> 0.950 | No clear effect |
| increase random features from 250 to 500 | RF-CDE and R-RDE · UEA | accuracy | Improved |
| reduce random features to 64 | RF-CDE · UEA | accuracy | No clear effect |
Closest papers by meaning
- Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions (ICLR 2025 · similarity 0.86)
- On the Generalization and Approximation Capacities of Neural Controlled Differential Equations (ICLR 2024 · similarity 0.85)
- In-Context Learning of Stochastic Differential Equations with Foundation Inference Models (NeurIPS 2025 · similarity 0.85)
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions (NeurIPS 2025 · similarity 0.84)
- Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference (ICML 2024 · similarity 0.84)
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data (ICLR 2024 · similarity 0.84)
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.
