Under alpha-local differential privacy, the maximal Fisher information equals roughly alpha^2/4 times the squared mean absolute score as alpha goes to zero, and an optimal extremal mechanism exists.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Factorization by extremal privacy mechanisms: new insights into efficiency
Under alpha-local differential privacy, the maximal Fisher information equals roughly alpha^2/4 times the squared mean absolute score as alpha goes to zero, and an optimal extremal mechanism exists.