Rough differential equations on manifolds via natural bundles

What the math gives to ML

The paper provides a coordinate-invariant way to evolve states under highly irregular drivers by augmenting ordinary vector fields with second-order branched rough-velocity coefficients. Its transferable asset is the local Davie expansion: a state transition uses both first-order driver increments and independent second-order iterated increments, with a remainder controlled by a fractional power of a path control. This suggests a rough residual or state-space block that explicitly models order-dependent interactions between input increments, while using the paper's jet composition rule to preserve behavior under smooth reparameterizations of the hidden state. The strongest initial test is a second-order sequence model on irregularly sampled or noisy streams, compared against a neural CDE or GRU block at equal parameter count and FLOPs.