Research map / Bandits and online learning / Online convex optimization and games
Information Directed Sampling for Stochastic Bandits With 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 IDS-N, IDSN-LP, and IDS-LP instead of TS-N (ablation) | Stochastic bandits with deterministic graph feedback · Deterministic graph feedback, time-invariant and time-variant | cumulative regret | Helped |
| Use IDS-N, IDSN-LP, and IDS-LP instead of TS-N (ablation) | Stochastic bandits with Erdős-Rényi random graph feedback · Random graph feedback, time-invariant and time-variant | average regret | Helped |
| Use IDS-LP instead of IDS-N or IDSN-LP (ablation) | IDS policies for graph feedback · Deterministic and random graph feedback | cumulative regret | Mixed |
| Use TS-N instead of UCB-N, UCB-maxN, or ε_t-greedy-LP | Stochastic bandits with deterministic graph feedback · Deterministic graph feedback | cumulative regret | Helped |
| Use IDS policies instead of Exp3-SET or Exp3-Res | Stochastic bandits with Erdős-Rényi random graph feedback · Random graph feedback | average regret | Helped |
Closest papers by meaning
- Thompson Sampling for Stochastic Bandits with Graph Feedback (AAAI 2017 · similarity 0.95)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.91)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.89)
- Efficient Graph Bandit Learning with Side-Observations and Switching Constraints (AAAI 2025 · similarity 0.89)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.88)
- On Interpolating Experts and Multi-Armed Bandits (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.