Research map / Bandits and online learning / Multi-armed bandits
A KL-LUCB algorithm for Large-Scale Crowdsourcing
Ervin Tanczos, Robert Nowak, Bob Mankoff
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 KL-based confidence bounds instead of sub-Gaussian bounds | lil-KLUCB · Synthetic Bernoulli rewards, α=1 | samples to find the best arm: about 20 % fewer samples | Improved |
| Use KL-based confidence bounds instead of sub-Gaussian bounds | lil-KLUCB · Synthetic Bernoulli rewards, α=1/2 | samples to find the best arm: 30 % fewer samples | Improved |
| Use KL-based confidence bounds instead of sub-Gaussian bounds | lil-KLUCB · New Yorker Caption Contest data, best-arm mean about 0.5 | empirical probability that the best arm is among the top 5 | No clear effect |
| Use KL-based confidence bounds instead of sub-Gaussian bounds | lil-KLUCB · New Yorker Caption Contest data, high best-arm mean | empirical probability that the best arm is among the top 5 | Improved |
| Use KL-based rather than sub-Gaussian confidence bounds | Best-arm identification with gaps Δᵢ=(i/n)^α · Theoretical sample-complexity scaling, α=1 | sample complexity: n log n vs n² | Improved |
| Use KL-based rather than sub-Gaussian confidence bounds | Best-arm identification with gaps Δᵢ=(i/n)^α · Theoretical sample-complexity scaling, α∈(1/2,1) | sample complexity: n vs n^(2α) | Improved |
| Use lil-KLUCB’s confidence-bound analysis rather than KL-LUCB’s | Best-arm identification with bounded rewards · Fixed-confidence best-arm identification | sample-complexity dependence on arm count and Chernoff information | Improved |
Closest papers by meaning
- Near Optimal Best Arm Identification for Clustered Bandits (ICML 2025 · similarity 0.86)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.86)
- Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · similarity 0.86)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · similarity 0.86)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.86)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.85)
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.
