For f misbehaving workers among n, data poisoning degrades the uniform stability of robust distributed (S)GD by Θ(f/(n-f)), while Byzantine failures degrade it by at least Ω(√(f/(n-2f))) for f ≥ n/3, implying strictly worse generalization.
Title resolution pending
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
-
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
For f misbehaving workers among n, data poisoning degrades the uniform stability of robust distributed (S)GD by Θ(f/(n-f)), while Byzantine failures degrade it by at least Ω(√(f/(n-2f))) for f ≥ n/3, implying strictly worse generalization.