Research map / Bandits and online learning / Multi-armed bandits
Optimal Regret of Bandits under Differential Privacy
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies regret minimisation in stochastic bandits under epsilon-global differential privacy, addressing the gap between known regret lower and upper bounds.
Problem
Regret minimisation in stochastic multi-armed bandits under epsilon-global differential privacy, where the best-known regret lower and upper bounds have a significant gap.
Approach
Closes the gap between known lower and upper regret bounds for epsilon-global DP stochastic bandits; the abstract is truncated, so the specific algorithmic mechanism is not stated.
Experimental setup
Metrics: regret
Closest papers by meaning
- When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits (NeurIPS 2022 · similarity 0.94)
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits (NeurIPS 2026 · similarity 0.91)
- Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret (ICML 2025 · similarity 0.91)
- Faster Rates for Private Adversarial Bandits (ICML 2025 · similarity 0.90)
- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements (ICML 2024 · similarity 0.89)
- Locally Private and Robust Multi-Armed Bandits (NeurIPS 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.