Date of Award
2002
Document Type
Thesis (Undergraduate)
Department or Program
Department of Computer Science
First Advisor
Javed A. Aslam
Abstract
Boosting is a means of using weak learners as subroutines to produce a strong learner with markedly better accuracy. Recent results showing the connection between logistic regression and boosting provide the foundation for an information-theoretic analysis of boosting. We describe the analogy between boosting and gambling, which allows us to derive a new upper bound on training error. This upper bound explicitly describes the effect of noisy data on training error. We also use information-theoretic techniques to derive an alternative upper-bound on testing error which is independent of the size of the weak-learner space.
Original Citation
Listed in the Dartmouth College Computer Science Technical Report Series as TR2002-428.
Recommended Citation
Lahaie, Sebastien M., "Information-theoretic Bounds on the Training and Testing Error of Boosting" (2002). Dartmouth College Undergraduate Theses. 205.
https://digitalcommons.dartmouth.edu/senior_theses/205
