A Gaussian-smoothing, Transformer, and DDPM denoising stack is claimed to cut MSE by up to 56.7% on zero-inflated precipitation forecasting, with a theoretical guarantee that does not hold.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction
A Gaussian-smoothing, Transformer, and DDPM denoising stack is claimed to cut MSE by up to 56.7% on zero-inflated precipitation forecasting, with a theoretical guarantee that does not hold.