Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.
The adaptive-step size solvers, such asHeun,Dopri5, &Tsit5, performed better than Eulermethod
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural CDEs as Correctors for Learned Time Series Models
Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.