Derives ODE deterministic equivalents and an adversarial homogenized SDE for SGD iterates in high-dim ℓ2-adversarial training, showing no constant learning rate ensures monotone descent for single-class adversarial least squares and equivalence to adaptive regularized standard SGD.
Adversarially robust general- ization just requires more unlabeled data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.
citing papers explorer
-
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
Derives ODE deterministic equivalents and an adversarial homogenized SDE for SGD iterates in high-dim ℓ2-adversarial training, showing no constant learning rate ensures monotone descent for single-class adversarial least squares and equivalence to adaptive regularized standard SGD.
-
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.