Research map / Bandits and online learning / Contextual bandits and Thompson sampling
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
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 |
|---|---|---|---|
| Use a determinant-based local communication trigger with fully independent agent-server communication | FedLinUCB · Federated contextual linear bandits (asynchronous) | regret: d\sqrt{T} \log T | Helped |
| Use a determinant-based local communication trigger | FedLinUCB · Federated contextual linear bandits (asynchronous) | communication complexity: d M^2\log T | Helped |
| Use lazy model updates, updating the policy only after communicating with the server | FedLinUCB · Federated contextual linear bandits (asynchronous) | switching cost: \tilde O(dM^2) | Helped |
| Use less than O(M/\log (T/M)) expected communications | Federated contextual linear bandit algorithms · Federated contextual linear bandits | regret: \Omega(d\sqrt{MT}) | Hurt |
Closest papers by meaning
- Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users (AAAI 2024 · similarity 0.93)
- Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost (ICML 2023 · similarity 0.92)
- Federated Linear Bandits with Finite Adversarial Actions (NeurIPS 2023 · similarity 0.91)
- Federated Linear Contextual Bandits (NeurIPS 2021 · similarity 0.91)
- Incentivized Communication for Federated Bandits (NeurIPS 2023 · similarity 0.91)
- Communication-Efficient Federated Non-Linear Bandit Optimization (ICLR 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.