For high-dimensional ridge regression, spurious correlations concentrate on a deterministic function of the data covariance and ridge penalty, creating a provable trade-off with in-distribution test loss.
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes
1 Pith paper cite this work. Polarity classification is still indexing.
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.
citation-role summary
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
For high-dimensional ridge regression, spurious correlations concentrate on a deterministic function of the data covariance and ridge penalty, creating a provable trade-off with in-distribution test loss.