Showing stat.MLShow all
2 papers · 1 filter
stat.ML2024
Adversarially robust generalization theory via Jacobian regularization for deep neural networks
Dongya Wu, Xin Li
Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian…
stat.ML2024
Sparse deep neural networks for nonparametric estimation in high-dimensional sparse regression
Dongya Wu, Xin Li
Generalization theory has been established for sparse deep neural networks under high-dimensional regime. Beyond generalization, parameter estimation is also important since it is…