ensemble-principle-operates-at-multiple-scales

IN derived (depth 2)

Created 2026-06-21T10:09:45+00:00 · Reviewed 2026-06-21T15:37:01+00:00

The ensemble principle is a fundamental generalization mechanism operating at multiple independent scales — explicitly in random forests and boosting which decompose bias-variance independently across separate models, and implicitly in dropout which samples from an exponential family of sub-networks within a single model — suggesting that model averaging is a structural property of robust learning, not just a technique.

Justifications

SL — Same variance-reduction-through-averaging mechanism appears in both multi-model and intra-model forms

Antecedents (all must be IN):

  • IN dropout-ensemble-interpretation — Dropout is implicitly an ensemble method within a single network — randomly omitting hidden units during training samples from an exponential family of sub-networks, connecting the probabilistic interpretation of neural networks to the variance-reducing properties of ensembles.
  • IN ensemble-methods-decompose-bias-variance-independently — Ensemble methods provide complementary and independent controls over the two components of prediction error: bagging (random forests) reduces variance by averaging decorrelated models, while boosting reduces bias by iteratively correcting residuals — together enabling targeted error reduction.

Dependents

These beliefs depend on this one: