Research map / Bandits and online learning / Multi-armed bandits
Robust Pure Exploration in Linear Bandits with Limited Budget
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 OptDesign-based experimental design (plus uniform-sampling comparison in GetArms) within sequential halving rounds | LinearExploration · Simulated linear bandit experiments (Figure 1) | probability of returning best arm | Helped |
| Remove adaptive rounds (single GetArms call spending full budget) (ablation) | LinearExploration · Simulated linear bandit experiments (Figure 1 and 2) | probability of returning best arm | Hurt |
| Increasing misspecification magnitude (||gamma||_inf up to 1/sqrt(d)) | LinearExploration · Simulated, T=80, n=20, d=3 | probability of returning best arm | Hurt |
Closest papers by meaning
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.92)
- Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms (ICML 2025 · similarity 0.91)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.90)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.90)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.90)
- Feasible Action Search for Bandit Linear Programs via Thompson Sampling (ICML 2025 · similarity 0.89)
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.