De-Han Wang

Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification

We study norm-constrained linear classification under Eu clidean adversarial perturbations in a Gaussian model with a low-dimen sional informative subspace and an independent noise tail. For bounded ramp loss, we prove that a principal-space witness with risk below one half forces every near-optimal predictor to have s...