REVIEW 2 cited by
Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Based on differential privacy (DP) framework, we introduce and unify privacy definitions for the multi-armed bandit algorithms. We represent the framework with a unified graphical model and use it to connect privacy definitions. We derive and contrast lower bounds on the regret of bandit algorithms satisfying these definitions. We leverage a unified proving technique to achieve all the lower bounds. We show that for all of them, the learner's regret is increased by a multiplicative factor dependent on the privacy level $\epsilon$. We observe that the dependency is weaker when we do not require local differential privacy for the rewards.
Forward citations
Cited by 2 Pith papers
-
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.
-
The Fair Game: Auditing & Debiasing AI Algorithms Over Time
Proposes 'Fair Game', a reinforcement-learning loop in which an auditor's bias criteria, updatable over time, steer a debiasing agent that adapts an ML model's predictions.
Discussion (0). Sign in to comment.