Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context
Osama Hanna, Lin Yang, Christina Fragouli
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 |
|---|---|---|---|
| central learner runs a single-context bandit algorithm on designed action set and sends parameter estimates, instead of agents sending contexts | Algorithm 1 (known context distribution) · distributed contextual linear bandit | communication per context: 0 bits per context | Improved |
| wrap LinUCB-type algorithm in Algorithm 1 with quantized 1-bit rewards | Algorithm 1 · distributed contextual linear bandit | regret | No clear effect |
| use Algorithm 2 with about 5d bits per context for unknown context distribution | Algorithm 2 · distributed contextual linear bandit | regret | Improved |
Closest papers by meaning
- Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost (ICML 2023 · similarity 0.93)
- Differentially Private Contextual Linear Bandits (NeurIPS 2018 · similarity 0.91)
- A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits (NeurIPS 2022 · similarity 0.91)
- Model Selection for Contextual Bandits (NeurIPS 2019 · similarity 0.91)
- Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit (NeurIPS 2024 · similarity 0.89)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · 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.
