Boosting foundations and algorithms

Foundations of machine learning -- Using AdaBoost to minimize training error -- Direct bounds on the generalization error -- The margins explanation for boosting's effectiveness -- Game theory, online learning, and boosting -- Loss minimization and generalizations of boosting -- Boosting, convex optimization, and information geometry -- Using confidence-rated weak predictions -- Multiclass classification problems -- Learning to rank -- Attaining the best possible accuracy -- Optimally efficient boosting -- Boosting in continuous time.;A remarkably rich theory has evolved around boosting, with connections to a range of topics including statistics, game theory, convex optimization, and information geometry. Boosting algorithms have also enjoyed practical success in such fields as biology, vision, and speech processing. At various times in its history, boosting has been perceived as mysterious, controversial, even paradoxical. This book, written by the inventors of the method, brings together, organizes, simplifies, and substantially extends two decades of research on boosting, presenting both theory and applications in a way that is accessible to readers from diverse backgrounds while also providing an authoritative reference for advanced researchers. With its introductory treatment of all material and its inclusion of exercises in every chapter, the book is appropriate for course use as well. --