ADANA thread: cooldown plus log-time weight decay puts AdamW's equivalent OT on a 1.15 slope

_katieeverett · x · 2026-09-10

Key thread result: log-time memory should in theory reach the loss in O(t) steps that fixed memory needs O(t^1.15) for; with both momentum cooldown and log-time weight decay, AdamW's measured equivalent overtraining roughly follows that 1.15 slope, matching DANA theory.

Related event: Momentum-Scheduled ADANA Changes Scaling Exponents on the Overtraining Axis(13 posts)→

Original post →

More from Research

Research channel →