REVIEW 1 cited by
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes
read the original abstract
Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we provide a precise study of the adversarial robustness in different scenarios, from initialization to the end of training in different regimes, as well as intermediate scenarios, where initialization still plays a role due to "lazy" training. We consider over-parameterized networks in high dimensions with quadratic targets and infinite samples. Our analysis allows us to identify new tradeoffs between approximation (as measured via test error) and robustness, whereby robustness can only get worse when test error improves, and vice versa. We also show how linearized lazy training regimes can worsen robustness, due to improperly scaled random initialization. Our theoretical results are illustrated with numerical experiments.
Forward citations
Cited by 1 Pith paper
-
Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
NPPR is the worst-case probability of correct classification over all perturbation distributions inside a budget; a Gaussian mixture model is fit to approximate it, giving conservative robustness estimates.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.