Locally private thresholding bandit algorithms achieve near-optimal error and sample complexity, matching new lower bounds for small privacy budgets.
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
-
Locally Differentially Private Thresholding Bandits
Locally private thresholding bandit algorithms achieve near-optimal error and sample complexity, matching new lower bounds for small privacy budgets.