Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Differentially Private Contextual Linear Bandits
Roshan Shariff, Or Sheffet
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 standard differential privacy instead of joint differential privacy | Contextual bandits · Contextual bandits under continual observation | pseudo-regret | Hurt |
| Use joint differential privacy with tree-based private history and LinUCB | Contextual linear bandits · Contextual linear bandits | pseudo-regret | Improved |
| Use Wishart noise rather than Gaussian noise | Tree-based private LinUCB · Contextual linear bandits | pseudo-regret bound dependence on ε | Mixed |
| Add a gap assumption separating optimal and suboptimal actions | Changing-regularizer LinUCB · Contextual linear bandits with reward gap Δ | pseudo-regret bound | Improved |
| Require private MAB algorithms to preserve ε-differential privacy | MAB algorithms · Stochastic MAB | additional pseudo-regret | Hurt |
Closest papers by meaning
- Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context (NeurIPS 2022 · similarity 0.91)
- Stochastic Bandits with Context Distributions (NeurIPS 2019 · similarity 0.91)
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Generalized Linear Bandits with Limited Adaptivity (NeurIPS 2024 · similarity 0.89)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.89)
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · 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.
