AI Paper Atlas

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

NeurIPS 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use a decreasing Hurst function instead of Brownian motion (H = 0.5) as the perturbation noiseScore-based generative model with fractional noise · MNIST generationNLL (bits/dim): 4.97 -> 3.79Improved
use H > 1/2 (long-range dependent noise) in the diffusion perturbationScore-based generative model with fractional noise · MNIST generationsample qualityHurt
increase number of observed sample paths from 1 to 5Learned Hurst function in neural SDE · Synthetic mBm SDE datacloseness of learned to true Hurst functionImproved
fractional-noise latent SDE vs Latent SDE with Brownian motion and Latent ODENeural SDE with learned Hurst function · Financial hourly stock data (AMZN, AAPL, GOOGL, MSFT)test NLL and RMSENo clear effect
use the proposed model instead of Latent SDE with Brownian noiseNeural SDE with learned Hurst function · Financial datatraining NLLImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy