The first study of unlearning in offline stochastic multi-armed bandits formalizes privacy constraints and delivers adaptive algorithms with performance guarantees and lower bounds for single- and multi-source scenarios under fixed-sample and distribution models.
arXiv preprint arXiv:1905.12298 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Derives privacy-dependent lower bounds for fixed-confidence BAI and gives asymptotically optimal DP Top-Two algorithms for local and global models.
citing papers explorer
-
Unlearning Offline Stochastic Multi-Armed Bandits
The first study of unlearning in offline stochastic multi-armed bandits formalizes privacy constraints and delivers adaptive algorithms with performance guarantees and lower bounds for single- and multi-source scenarios under fixed-sample and distribution models.
-
Differentially Private Best-Arm Identification
Derives privacy-dependent lower bounds for fixed-confidence BAI and gives asymptotically optimal DP Top-Two algorithms for local and global models.