Bias-variance decomposition expresses the expected squared error of an estimator f̂ for target f(x) under loss (y−f̂(x))² as E[(y−f̂)²] = Bias²(f̂) + Var(f̂) + σ², where Bias² = (E[f̂]−f)², Var = E[(f̂−E[f̂])²], and σ² is irreducible noise variance. Parameters are the data-generating distribution, the estimator class, and the loss function; it persists as a canonical teaching tool and design principle for model selection in statistics and machine learning. [formal: bias-variance decomposition | substrate: mind | horizon: as-long-as-us | explicit: yes | epoch: 0.99]
Accepted ontology entry
bias-variance-decomposition
Bias-variance decomposition expresses the expected squared error of an estimator f̂ for target f(x) under loss (y−f̂(x))² as E[(y−f̂)²] = Bias²(f̂) + Var(f̂) + σ², where Bias² = (E[f̂]−f)², Var = E[(f̂−E[f̂])²], and σ² is irreducible noise…
Definition
Why it is in scope
A human-made mathematical identity that splits the expected prediction error of a statistical estimator into bias squared, variance, and irreducible error, persisting in machine learning theory and teaching.
Names and aliases
- bias-variance-decompositionen · CANONICAL
Relations from this entry
- cms7xukk2007xh6s8dqyihtf7SERVES →
The bias-variance decomposition breaks prediction error into bias, variance, and irreducible error components. This decomposition serves model selection by guiding the choice of model complexity — helping practitioners navigate the bias-variance tradeoff to select models that generalize well. Law 8d: servant (decomposition) points at master (model selection).
- varianceDEPENDS_ON →
Bias-variance decomposition is defined in terms of Var(f̂) as a component of the expected squared error. Remove variance from the mathematical vocabulary and the decomposition cannot be expressed or evaluated operationally; the formula ceases to operate. Law 8b removal test satisfied.
- statistical-modelDEPENDS_ON →
Bias-variance decomposition is computed on predictions of a statistical model; remove the model and the decomposition has no data to operate on.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Sep 4, 2026, 4:03 PM UTC
- Content hash
- 6a527972c258db996ebe466844dc8234132cb58fd14f57d06ecd09a6da4a077e