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.
ForL∼ N(0,4v 4 2β2(n−2f)), we apply the Gaussian tail boundexp(− (tA/2)2 2σ2 L ), EL := min δ2U2 12 18432v4 2β2(n−2f)(d−1) 2 , δU12 768v4 2β2(n−2f)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.