Accession Number:

ADA459843

Title:

Bagging Regularizes

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Report Date:

2002-03-01

Pagination or Media Count:

9.0

Abstract:

Intuitively, we expect that averaging - or bagging - different regressors with low correlation should smooth their behavior and be somewhat similar to regularization. In this note we make this intuition precise. Using an almost classical definition of stability, we prove that a certain form of averaging provides generalization bounds with a rate of convergence of the same order as Tikhonov regularization - similar to fashionable RKHS-based learning algorithms,

Subject Categories:

  • Statistics and Probability
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE