Adding a Wasserstein DRO gradient penalty to Mixup, AugMix, or NoisyMix raises average CIFAR-C accuracy by about 1.1% and PGD robustness on MNIST and Fashion-MNIST by 5-7%.
Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Adding a Wasserstein DRO gradient penalty to Mixup, AugMix, or NoisyMix raises average CIFAR-C accuracy by about 1.1% and PGD robustness on MNIST and Fashion-MNIST by 5-7%.