Boosted CV aR Classification (Supplementary Material)

On the COMP AS dataset, we use a three-layer feed-forward neural network activated by ReLU as the classification model. For optimization we use momentum SGD with learning rate 0.01 and The batch size is 128. On the CelebA dataset, we use a ResNet18 as the classification model. The remaining 45000 training samples consist the training set. The batch size is 128.