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.
- Final height: gap Δλ/N — LOO-CV is inconsistent (Shao 1993)
- Last-half tail: Δλ·log 2 — constant
- Total area: Δλ·log N — grows without bound
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.
More from Research
- Waterloo deep learning theory lecture notes on neural network scaling limits released — thegautamkamath · 2026-09-09
- Anthropic's first economics paper models transformative AI scenarios with 15% annual GDP growth — soumitrashukla9 · 2026-09-09
- Ben Lorica: Your Model Is a Rental, the Improvement Loop Is the Asset—Forget RSI Hype — bigdata · 2026-09-09
- In 2000, Alain Connes Said the Millennium Problems Were 'Totally Inaccessible to Computers' — minilek · 2026-09-09
- Researcher calls for mathematically defined problem lists in every field, citing AI's scalable verification — ValerioCapraro · 2026-09-09
- Dev Spotlight: Transformers Forced to Predict Themselves and Build Belief States — yacinelearning · 2026-09-09