Research map / Bandits and online learning / Multi-armed bandits
Multi-Fidelity Multi-Armed Bandits Revisited
Xuchuang Wang, Qingyun Wu, Wei Chen, John C.S. Lui
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 |
|---|---|---|---|
| use Explore-A (UCB search for optimal fidelity) instead of Explore-B (good-fidelity explore-then-commit) | LUCB framework for multi-fidelity BAI · Simulated MF-MAB, K=5, M=3 | cost complexity | Improved |
| use Explore-B instead of Explore-A when another fidelity has near-equal efficiency | LUCB framework for multi-fidelity BAI · Simulated MF-MAB, K=5, M=5 | cost complexity | Improved |
| add a third procedure Explore-C that needs no prior knowledge of top-two arm means | LUCB framework for multi-fidelity BAI · theoretical bound | cost complexity upper bound | Mixed |
| reduce multi-fidelity BAI to a single fidelity with unit cost (M=1, lambda=1) | Explore-A and Explore-B bounds · classic MAB BAI | sample complexity bound | No clear effect |
| explore at highest fidelity and exploit at lowest fidelity in an elimination algorithm | MF-MAB regret minimization · worst-case regret | regret upper bound | Improved |
Closest papers by meaning
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.93)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.92)
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.91)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · similarity 0.90)
- On Interpolating Experts and Multi-Armed Bandits (ICML 2024 · similarity 0.90)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.90)
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.
