2 papers
cs.LG2026
Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics
Tiexin Ding
Building on a two-parameter Weibull framework for diagnosing transformer weight distributions, we study why the Weibull weight-scale parameter grows, overshoots, and then rela…
cs.LG2026
A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions
Tiexin Ding
We apply the Weibull distribution -- a two-parameter family from extreme-value theory -- as a diagnostic framework for element-wise weight magnitude distributions in transformers.…