Research map / Bandits and online learning / Multi-armed bandits
Efficient Pure Exploration in Adaptive Round model
Tianyuan Jin, Jieming SHI, Xiaokui Xiao, Enhong Chen
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 |
|---|---|---|---|
| delta-E instead of ME | delta-E · PAC best arm | query cost: 100 times | Improved |
| delta-ER (R=2 rounds) instead of ME | delta-ER · PAC best arm | query cost: 10 times | Improved |
| hard round limit R=2 (delta-ER) vs no limit (delta-E) | delta-ER · PAC best arm | query cost: 100 times -> 10 times | Hurt |
| delta-E instead of ME in rounds | delta-E · PAC best arm | rounds: 11 -> 2.2 | Improved |
| k-delta-ER instead of ME-AS | k-delta-ER · PAC top-20 | query cost: 100 times | Improved |
| k-delta-E instead of ME-AS | k-delta-E · PAC top-20 | query cost: 1000 times | Improved |
| k-delta-E instead of ME-AS in rounds | k-delta-E · PAC top-20 | rounds: 6 -> 2.1 | Improved |
| EG-delta-E instead of Elimination [8] | EG-delta-E · Exact top-k | query cost: 250 times | Improved |
| EG-delta-E instead of Elimination [8] in rounds | EG-delta-E · Exact top-k Normal | rounds: 36 -> 21 | Improved |
| EG-delta-E instead of UCB [17] | EG-delta-E · Exact top-k | query cost | No clear effect |
Closest papers by meaning
- Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids (ICLR 2025 · similarity 0.88)
- Near Optimal Non-asymptotic Sample Complexity of 1-Identification (ICML 2025 · similarity 0.88)
- The Batch Complexity of Bandit Pure Exploration (ICML 2025 · similarity 0.88)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.88)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.86)
- On Universally Optimal Algorithms for A/B Testing (ICML 2024 · similarity 0.86)
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.
