Linear NCDEs replace non-linear vector fields with linear ones, enabling parallel-in-time training via associative scans while retaining maximal theoretical expressivity and achieving state-of-the-art time series performance at up to 1000x speedup.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Advances in Neural Controlled Differential Equations
Linear NCDEs replace non-linear vector fields with linear ones, enabling parallel-in-time training via associative scans while retaining maximal theoretical expressivity and achieving state-of-the-art time series performance at up to 1000x speedup.