SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

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 small tail weight. A path-specific density bound yields constants without requiring positive tail variance. Under isotropic principal covariance, we establish a unique population minimizer and joint local growth. Boundary normalization then removes the common attack penalty from c

Read original source ↗ Open in workspace

recordType

paper

region

Global