Sign in
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization.
Songyang Gao
Shihan Dou
Yan Liu
Xiao Wang
Qi Zhang
Zhongyu Wei
Jin Ma
Ying Shan
Published in:
ACL (1) (2023)
Keyphrases
</>
risk minimization
loss function
empirical risk
training process
training set
generalization error
training and test data
uniform convergence
cross validation
line search
multi category
hinge loss
training algorithm
decision trees
data distribution
support vector
multi agent
learning algorithm