Research map / Bandits and online learning / Online convex optimization and games
Federated Online and Bandit Convex Optimization
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 |
|---|---|---|---|
| Collaboration via communication (vs. independent OGD per machine) under first-order feedback | distributed OGD on Lipschitz and smooth convex functions against adaptive adversary · adaptive adversary, intermittent communication | min-max average regret | No clear effect |
| Add the one-point projected bandit gradient estimator with unprojected lazy update (FedPOSGD) | federated adversarial linear bandits · adversarial linear bandits, high dimension d | average regret bound | Helped |
| Switch from one-point to two-point bandit feedback (FedOSGD) | federated adversarial linear bandits · adversarial linear bandits | regret bound dependence on d and ζ | Helped |
| Collaboration with two-point feedback (FedOSGD) vs non-collaborative baseline | federated linear bandits / Lipschitz convex bandits · high dimension d >= K^2 M^2 | average regret | Helped |
| Small heterogeneity ζ in the two-point bound for linear functions | FedOSGD on linear functions · adversarial linear bandits | average regret bound | Helped |
| Small heterogeneity ζ in FedPOSGD bound | FedPOSGD · adversarial linear bandits, high dimension | average regret bound | No clear effect |
Closest papers by meaning
- Communication-Efficient Federated Non-Linear Bandit Optimization (ICLR 2024 · similarity 0.91)
- A Near-Optimal Best-of-Both-Worlds Algorithm for Federated Bandits (ICLR 2026 · similarity 0.91)
- Revisiting Decentralized Online Convex Optimization with Compressed Communication (NeurIPS 2026 · similarity 0.89)
- Federated X-armed Bandit (AAAI 2024 · similarity 0.88)
- Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications (NeurIPS 2026 · similarity 0.88)
- On the Necessity of Collaboration for Online Model Selection with Decentralized Data (NeurIPS 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.