A PAC-Bayesian bound ties worst-class robust error to the spectral norm of a robust confusion matrix, and a new spectral regularizer improves robust fairness.
A reductions approach to fair classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Robust Fairness via Confusional Spectral Regularization
A PAC-Bayesian bound ties worst-class robust error to the spectral norm of a robust confusion matrix, and a new spectral regularizer improves robust fairness.