DATE: Wed, Mar 18, 2020 Postponed
TIME: 1 pm
PLACE: SITE 5084
TITLE: MixUp as directional adversarial training
PRESENTER: Yongyi Mao
University of Ottawa
ABSTRACT:

In this talk I will present a joint recent work with Guillaume P. Archambault, Harry Guo, and Richong Zhang. In this work, we explain the working mechanism of MixUp in terms of adversarial training. We introduce a new class of adversarial training schemes, which we refer to as directional adversarial training, or DAT. In a nutshell, a DAT scheme perturbs a training example in the direction of another example but keeps its original label as the training target. We prove that MixUp is equivalent to a special subclass of DAT, in that it has the same expected loss function and corresponds to the same optimization problem asymptotically. This understanding not only serves to explain the effectiveness of MixUp, but also reveals a more general family of MixUp schemes, which we call Untied MixUp. We prove that the family of Untied MixUp schemes is equivalent to the entire class of DAT schemes. We establish empirically the existence of Untied Mixup schemes which improve upon MixUp.