Research map / Bandits and online learning / Online convex optimization and games
Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
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 the proposed time-varying exploration-exploitation trade-off and environment test | Online learning with general graph feedback · Stochastic general graph feedback | regret upper bound: O\bracket{ |D|^2 \cdot \max_{i:i\neq i^*}\bracket{ \frac{\log T/\delta}{\Delta_i^2} }^{\frac{3}{2}} } | Helped |
| Use the proposed time-varying exploration-exploitation trade-off and environment test | Online learning with general graph feedback · Adversarial general graph feedback | expected regret upper bound: O\bracket{K^{\frac{2}{3}} |D|^{\frac{1}{3}} T^{\frac{2}{3}}\sqrt{\log\frac{T}{\delta}}} | Helped |
| Use γ=1 before identifying the optimal arm and γ=0 afterward, before starting Exp3.G (ablation) | BoBW with General Graph Feedback · Adversarial general graph feedback | regret upper bound: O(T) | Hurt |
| Use γ=T^{-1/3} before starting Exp3.G (ablation) | BoBW with General Graph Feedback · Stochastic general graph feedback | regret upper bound: O(T^{1/3}\log T) | Hurt |
Closest papers by meaning
- A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs (NeurIPS 2022 · similarity 0.94)
- Stochastic Graphical Bandits with Adversarial Corruptions (AAAI 2021 · similarity 0.93)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.91)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.89)
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · similarity 0.88)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (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.