Model complexity gap drives three separation rates; LOO-CV is inconsistent

BlackHC · x · 2026-09-09

BlackHC discusses loss separation rates in model selection: with equal loss floors, models separate at three distinct rates, where Δλ is the model complexity delta.

He argues that "best model" is incomplete until we specify which part of learning and deployment we value. The full post covers the exact identity, the flip-order result, the regimes behind crossings, plus a toy experiment and an interactive panel.

Related event: Bayesian Model Selection Explains Why Proxy-Scale Winners Fail at Target Scale(10 posts)→

Original post →

More from Research

Research channel →