@TechReport{Dartmouth:TR2002-428,
  author = {Sebastien M. Lahaie},
  title = {{Information-theoretic Bounds on the Training and Testing Error of Boosting}},
  institution = {Dartmouth College, Computer Science},
  address = {Hanover, NH},
  number = {TR2002-428},
  year = {2002},
  month = {May},
  URL = {http://www.cs.dartmouth.edu/reports/TR2002-428.ps.Z},
  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.
  }
}