Login / Signup
Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training.
Zihui Wu
Haichang Gao
Bingqian Zhou
Xiaoyan Guo
Shudong Zhang
Published in:
CoRR (2022)
Keyphrases
</>
bregman divergences
mahalanobis distance
closed form
supervised learning
training examples
maximum entropy
cost sensitive
exponential family
theoretical guarantees
decision trees
support vector
training set
data points
principal component analysis
euclidean distance