A Statistical View to Boosting



Friday, 16 August 2013, 16:00 to 17:30


  • D-405 (D-Block Seminar Room)


In machine learning, AdaBoost has been an extremely popular boosting algorithm to improve the performance of ``weak learners". AdaBoost was initially proposed by Schapire and Freund from an algorithmic perspective. The statistical machine learners (who maintain that all machine learning algorithms are derived from a statistical framework) remained  skeptical of AdaBoost until Freidman et.al gave a statistical view of boosting and proved that boosting is equivalent to fitting additive models.

We will study this generalized boosting models and obtain AdaBoost as a specialized version.