A locally private collision-probability estimator with near-optimal sample complexity is given, but the sequential testing algorithm is mis-centered by a factor of two and its main theorem is false as stated.
Identity testing for mallows model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Near-optimal algorithms for private estimation and sequential testing of collision probability
A locally private collision-probability estimator with near-optimal sample complexity is given, but the sequential testing algorithm is mis-centered by a factor of two and its main theorem is false as stated.