Preprint
Aug 2026
When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version
This study examines how forecast quality evolves throughout reverse diffusion to find that general temporal structure is often recovered at relatively high noise levels, whereas continued low-noise refinement can introduce statistical drift and degrade the final forecast.
Dat Nguyen-Cong, L. Tran, T. Kieu
· 0 citations