Construct · 1 fields · 1 citations

bagging: a standalone construct

One name. One construct. A landmark on the map.

● anchor · one construct, one field Nearest construct by meaning·not indexed
bagging1 CONSTRUCTBaggingBREIMAN · 1996

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Machine learning

Average models trained on bootstrap resamples to cut variance

Bagging, short for bootstrap aggregating, is an ensemble technique that trains many copies of a model on different bootstrap resamples of the training data and then combines their predictions by averaging, for regression, or voting, for classification. Because the resamples differ, the models' errors partly cancel, which lowers variance and stabilises otherwise unstable learners such as decision trees. Breiman's 1996 Bagging predictors introduced the method. The referent is this resample-and-aggregate procedure, the building block that random forests later extended with random feature selection.[1]

Unit
The number of bootstrap-resampled models whose predictions are combined
Recovery means
Not applicable
Measured by
Assessed by the variance reduction and accuracy gain over a single model, often using out-of-bag error

Next

Run it through the Collider, or take the citations with you.

See how bagging sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this entry

Nearby constructs

boosting2 fields · 2 citationsjingle · one word, two constructsensemble3 fields · 6 citationsjingle · one word, three constructsblock3 fields · 6 citationsjingle · one word, three constructs

References

  1. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. https://doi.org/10.1007/BF00058655

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct