NoRIN
NoRIN
Auto-generated stub. Edit this file to add more details.
A non-linear reversible normalization framework utilizing Johnson S_U transforms with decoupled shape parameter optimization to reshape time-series distributions.
Why It Matters
Addresses the limitation of linear reversible normalization (RevIN) by enabling non-linear distribution shaping, critical for complex time-series data.
Evidence
We propose NoRIN, a non-linear reversible normalization based on the arcsinh-form Johnson S_U transform with two shape parameters (δ,ε) that control tailedness and skewness
Related Papers
Metadata & Links
- created_at
- 2026-05-14T06:08:44Z