Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

arXiv:2402.14989v1 Announce Type: new
Abstract: Irregular sampling intervals and missing values in real-world time series data present challenges for conventional methods that assume consistent intervals and complete data. Neural Ordinary Differential Equations (Neural ODEs) offer an alternative approach, utilizing neural networks combined with ODE solvers to learn continuous latent representations through parameterized vector fields. Neural Stochastic Differential Equations (Neural SDEs) extend Neural ODEs by incorporating a diffusion term, although this addition is not trivial, particularly when addressing irregular intervals and …

abstract arxiv challenges consistent continuous cs.ai cs.lg data differential learn missing values networks neural networks ordinary sampling series stochastic time series type values world