Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Learning Fractional White Noises in Neural Stochastic Differential Equations
Anh Tong, Thanh Nguyen-Tang, Toan Tran, Jaesik Choi
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 |
|---|---|---|---|
| use a decreasing Hurst function instead of Brownian motion (H = 0.5) as the perturbation noise | Score-based generative model with fractional noise · MNIST generation | NLL (bits/dim): 4.97 -> 3.79 | Improved |
| use H > 1/2 (long-range dependent noise) in the diffusion perturbation | Score-based generative model with fractional noise · MNIST generation | sample quality | Hurt |
| increase number of observed sample paths from 1 to 5 | Learned Hurst function in neural SDE · Synthetic mBm SDE data | closeness of learned to true Hurst function | Improved |
| fractional-noise latent SDE vs Latent SDE with Brownian motion and Latent ODE | Neural SDE with learned Hurst function · Financial hourly stock data (AMZN, AAPL, GOOGL, MSFT) | test NLL and RMSE | No clear effect |
| use the proposed model instead of Latent SDE with Brownian noise | Neural SDE with learned Hurst function · Financial data | training NLL | Improved |
Closest papers by meaning
- Variational Inference for SDEs Driven by Fractional Noise (ICLR 2024 · similarity 0.90)
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data (ICLR 2024 · similarity 0.87)
- Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributions (ICLR 2025 · similarity 0.86)
- Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions (NeurIPS 2025 · similarity 0.86)
- Generative Fractional Diffusion Models (NeurIPS 2024 · similarity 0.86)
- Heavy-Tailed Diffusion with Denoising Levy Probabilistic Models (ICLR 2025 · similarity 0.85)
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.
