Three selection criteria separate at different rates — LOO-CV is inconsistent

BlackHC · x · 2026-09-09

Quantitative result from the thread: with equal loss floors, models separate at three different rates (Δλ is the model complexity delta):

Conclusion: "best model" is incomplete until you specify which part of learning and deployment you value. The full post includes the exact identity, flip-order results, crossing regimes, 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 →