In Byzantine-robust LDP distributed learning, generalization error decreases with increasing privacy strength in high-noise regimes but increases in low-noise regimes, shown via matching algorithmic stability bounds.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
FB-NLL decouples user clustering from training dynamics by using subspace similarity on feature covariances and corrects noisy labels via directional alignment in learned feature space.
Random pixel permutation destroys local correlations in images, causing standard CNN classification accuracy to drop depending on class similarities while dilated convolutions recover some performance.
citing papers explorer
-
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
In Byzantine-robust LDP distributed learning, generalization error decreases with increasing privacy strength in high-noise regimes but increases in low-noise regimes, shown via matching algorithmic stability bounds.
-
FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning
FB-NLL decouples user clustering from training dynamics by using subspace similarity on feature covariances and corrects noisy labels via directional alignment in learned feature space.