AI RESEARCH
NoRIN: Backbone-Adaptive Reversible Normalization for Time-Series Forecasting
arXiv CS.LG
•
ArXi:2605.10823v1 Announce Type: new Reversible instance normalization (RevIN) and its successors (Dish-TS, SAN, FAN) have become the de facto plug-in for time-series forecasting, yet the map they apply to each data point is strictly affine, $x \mapsto ax+b$, so they cannot reshape the underlying distribution -- heavy tails remain heavy and skewness remains uncorrected.