Contraction versus Recurrence: An Exponential Separation in Observation-Based Prediction of Deterministic Dynamics
arXiv:2607.14885
2026
Dynamics
2 ideas extracted · analyzed Aug 30, 2026
What the math gives to ML
The paper establishes an exponential separation between recurrence-based prediction and observer-based state estimation. Recurrence requires expected return time scaling as \(\varepsilon^{-d}\), while a detectable observer reaches error \(\varepsilon\) in logarithmic time controlled by the closed-loop spectral radius. The transferable mechanism is a learned latent observer with explicitly contractive correction dynamics. This can replace expensive analogue retrieval and provides a falsifiable prediction for burn-in time and stability.
Ideas from this paper
✗ Failed on benchmark
2026
Replace recurrence or nearest-neighbour analogue lookup with a learned delay-coordinate observer that continuously corrects a latent state using the current observation. Constrain the observer's closed-loop Jacobian or linear state matrix to have spectral radius below one, so prediction error contracts geometrically and required burn-in grows logarithmically with target accuracy.
Useful8/10
Difficulty5/10
Novelty6/10
△ Mechanism confirmed, baseline not beaten
2026
Use the observer contraction rate as an online inference controller. Run the latent observer when its estimated contraction is strong, and invoke expensive retrieval or latent-state reinitialization only when contraction is weak or observation residuals indicate model mismatch.
Useful7/10
Difficulty5/10
Novelty7/10