Research map / Bandits and online learning / Online convex optimization and games
Learning on the Edge: Online Learning with Stochastic Feedback Graphs
Emmanuel Esposito, Federico Fusco, Dirk van der Hoeven, Nicolò Cesa-Bianchi
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 |
|---|---|---|---|
| Estimate unknown edge probabilities, choose a threshold, and reduce learning to a deterministic feedback-graph problem | \explore · Stochastic feedback graphs with local realized out-neighborhood feedback | regret: \min\left\{\sqrt{({\alpha^*}/{\varepsilon_s^*})T}, \bigl({\delta^*}/{\varepsilon_w^*}\bigr)^{1/3} T^{2/3}\right\} | Improved |
| Observe the realization of the entire feedback graph and use weighted graph parameters | Online learning with stochastic feedback graphs · Stochastic feedback graphs, entire realized graph observed | regret: \min \Biggl\{ T,\, &\min_{\varepsilon} \Bigl\{ \sqrt{\alpha_\mathsf{w}(\mathcal{G}_\varepsilon)T} ... , \min_{\varepsilo | Improved |
| Allow edge-specific probabilities without requiring prior knowledge of the stochastic graph | Online learning with stochastic feedback graphs · Stochastic feedback graphs | regret | Improved |
Closest papers by meaning
- A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs (NeurIPS 2022 · similarity 0.94)
- Stochastic Online Learning with Probabilistic Graph Feedback (AAAI 2020 · similarity 0.93)
- Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality (NeurIPS 2022 · similarity 0.93)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.90)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.89)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (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.
