Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Neural SDEs as Infinite-Dimensional GANs
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 a neural SDE GAN instead of CTFP or Latent ODE | Google/Alphabet stocks · Google/Alphabet stocks | Classification: 0.165 -> 0.357; 0.000239 -> 0.357 | Helped |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Google/Alphabet stocks · Google/Alphabet stocks | Prediction: 0.725 -> 0.144; 46.2 -> 0.144 | Helped |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Google/Alphabet stocks · Google/Alphabet stocks | MMD: 2.70 -> 1.92; 60.4 -> 1.92 | Helped |
| Use a neural SDE GAN instead of the strongest baseline, CTFP | Beijing Air Quality · Beijing Air Quality | Classification: 0.764 -> 0.589 | Hurt |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Beijing Air Quality · Beijing Air Quality | Prediction: 0.810 -> 0.395; 0.456 -> 0.395 | Helped |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Beijing Air Quality · Beijing Air Quality | MMD: 0.00198 -> 0.000160; 0.000242 -> 0.000160 | Helped |
| Use a neural SDE GAN instead of the strongest baseline, CTFP | Weights trained via SGD · Weights trained via SGD | Classification: 0.676 -> 0.507 | Hurt |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Weights trained via SGD · Weights trained via SGD | Prediction: 0.0808 -> 0.00843; 0.127 -> 0.00843 | Helped |
| Use a neural SDE GAN instead of CTFP or Latent ODE | Weights trained via SGD · Weights trained via SGD | MMD: 12.0 -> 5.28; 23.2 -> 5.28 | Helped |
| Add final tanh nonlinearities to drift and diffusion fields (ablation) | Neural SDE models · Stocks, Beijing Air Quality, and weights | performance | Helped |
| Average generator and discriminator weights over training (ablation) | Neural SDE GAN · Stocks, Beijing Air Quality, weights, and Ornstein–Uhlenbeck | performance | Helped |
| Use Adadelta instead of the other tested standard optimizers (ablation) | Neural SDE GAN · Experiments | performance | Helped |
Closest papers by meaning
- Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions (ICLR 2025 · similarity 0.90)
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data (ICLR 2024 · similarity 0.90)
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions (NeurIPS 2025 · similarity 0.88)
- SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations (ICML 2025 · similarity 0.87)
- SING: SDE Inference via Natural Gradients (NeurIPS 2025 · similarity 0.86)
- On the Generalization and Approximation Capacities of Neural Controlled Differential Equations (ICLR 2024 · similarity 0.86)
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.