SOURCE-LINKED INTELLIGENCE

Leaky-integrator reconstruction: taming error accumulation in recursive differenced time-series forecasting

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

We introduce leaky-integrator reconstruction, a training-free method that cures the error accumulation of recursive differenced forecasting. Our first contribution is diagnostic: predicting one-step changes and integrating them by cumulative summation, the standard remedy for non-stationarity, is a discrete integrator with a pole on the unit circle, and we show this makes recursive rollout of a nonlinear model diverge, its 336-step error reaching several times that of a well-behaved forecaster (normalised MAE 1.6-3.8 versus about 0.8) across every neural architecture tested. Our second, centra

Read original source ↗ Open in workspace

recordType

paper

region

Global