The authors give an efficient non-interactive L-LDP algorithm for SCO achieving excess risk O(sqrt(K/(ε n))) in high privacy and O(sqrt(K/(e^ε n))) in medium privacy, with matching information-theoretic lower bounds for large n.
Theorem 4((Duchi et al., 2013)).LetQ be a (publicly known) d-dimensional subspace of Rm and L>
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convex Optimization with Local Label Differential Privacy: Tight Bounds in All Privacy Regimes
The authors give an efficient non-interactive L-LDP algorithm for SCO achieving excess risk O(sqrt(K/(ε n))) in high privacy and O(sqrt(K/(e^ε n))) in medium privacy, with matching information-theoretic lower bounds for large n.