Research map / Federated learning and privacy / Differential privacy
DP-NCB: Privacy Preserving Fair Bandits
Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use GDP-NCB instead of AdaP-UCB | global DP bandit · 2 Bernoulli arms, means (2e)^-T and 1 | Nash regret | Improved |
| use GDP-NCB instead of AdaP-UCB | global DP bandit · 50 Bernoulli arms, epsilon 0.2 | Nash regret | Improved |
| use LDP-NCB instead of LDP-UCB | local DP bandit · 50 Bernoulli arms, epsilon 0.2 | Nash regret | Improved |
| decrease privacy budget epsilon (ablation) | GDP-NCB and LDP-NCB · 50 Bernoulli arms | Nash regret | Hurt |
| add global DP noise to NCB | non-private NCB · 50 Bernoulli arms | Nash regret decay rate | Hurt |
| switch from global to local DP | DP-NCB · 50 Bernoulli arms | Nash regret decay rate | Hurt |
| use heterogeneous reward distributions (Bernoulli, Beta, two-point, uniform) | GDP-NCB, LDP-NCB · 50 mixed-distribution arms | Nash regret trend | No clear effect |
Closest papers by meaning
- Locally Private and Robust Multi-Armed Bandits (NeurIPS 2024 · similarity 0.90)
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits (NeurIPS 2026 · similarity 0.89)
- On Differentially Private Federated Linear Contextual Bandits (ICLR 2024 · similarity 0.89)
- Differentially Private Reinforcement Learning with Self-Play (NeurIPS 2024 · similarity 0.89)
- Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret (ICML 2025 · similarity 0.89)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.88)
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.
