Building Robust Ensembles via Margin Boosting

This lecture explores the concept of building robust ensembles through margin boosting, focusing on adversarial attacks and defenses in machine learning models. The instructor presents the theory behind margin boosting and its application to creating adversarially robust ensembles. The lecture covers the optimization of the robust margin boosting game, the development of the MRBoost algorithm, and the use of the Margin Cross Entropy loss for improved adversarial defense. Experimental results and theoretical guarantees are discussed, showcasing the effectiveness of the proposed approach.