Renormalizing probability scores destroys calibration, dev warns in model training debate

spikedoanz · x · 2026-09-17

In a reply to a proposal to simply renormalize scores (adding just a few ms), spikedoanz argues this is no way to build a coherent prediction model: renormalization turns (0.09, 0.01) into exactly (0.9, 0.1), when the model should really signal uncertainty (0.5, 0.5). Training with KL on such independently sampled scalars would likely drive the model insane.

Related event: Developers Warn Against Training on Renormalized Probability Scores(2 posts)→

Original post →

More from Research

Research channel →