bias-variance-tradeoff-prediction-error

IN premise — entries/2026/06/21/wiki-Supervised_learning-chunk-1.md

Created 2026-06-21T09:55:53+00:00

In supervised learning, prediction error decomposes approximately as bias + variance: flexible models have low bias but high variance, rigid models have high bias but low variance

Dependents

These beliefs depend on this one:

• IN classical-generalization-theory-overturned — Classical generalization theory — the U-shaped bias-variance tradeoff — has been overturned by two empirical phenomena: double descent shows test error decreasing again far past the interpolation threshold, and benign overfitting shows perfect training fit coexisting with good generalization in overparameterized regimes.
• IN no-universal-optimal-model — No universally optimal ML model exists: the No Free Lunch theorem establishes this impossibility in principle, and the bias-variance decomposition reveals the mechanism — any fixed model trades bias against variance depending on the problem.