Research map / Bandits and online learning / Multi-armed bandits
Achieving Privacy in the Adversarial Multi-Armed Bandit
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add Laplace noise to each gain before EXP3 observes it | EXP3 · Oblivious adversarial bandits | expected regret: O{T^{2/3} /ε} -> O{√T lnT /ε} | Helped |
| Run EXP3 in fixed-size batches and feed it the average gain per batch | EXP3 · Switching costs adversary | expected regret: O{T^{3/4}} -> O{T^{2/3}} | Helped |
| Run EXP3 in fixed-size batches and use its inherent action-selection privacy | EXP3 · Oblivious adversarial bandits | cumulative privacy loss: O{2T} -> O{√ln T} | Helped |
| Use EXP3τ instead of DPEXP3-Laplace | Private adversarial bandit algorithms · Oblivious adversary or a weaker adversary | regret | Hurt |
| Use EXP3τ instead of EXP3 or DPEXP3-Laplace | Private adversarial bandit algorithms · Switching costs adversary | regret | Helped |
Closest papers by meaning
- Faster Rates for Private Adversarial Bandits (ICML 2025 · similarity 0.91)
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits (NeurIPS 2026 · similarity 0.88)
- Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy (NeurIPS 2026 · similarity 0.88)
- Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret (ICML 2025 · similarity 0.87)
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.87)
- The Limits of Differential Privacy in Online Learning (NeurIPS 2024 · similarity 0.86)
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.