Research map / Bandits and online learning / Multi-armed bandits
Optimal Clustering with Noisy Queries via Multi-Armed Bandit
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 multi-armed bandit best-arm identification to identify each vertex's cluster instead of querying a fixed number of representatives from every cluster | Noisy clustering · Noisy clustering, nearly balanced instances | query complexity: O(\frac{nk\log n}{\delta^2}) -> O(\frac{n(k+\log n)}{\delta^2}) | Helped |
| Use multi-armed bandit identification with iterative filtering and cluster merging | NoisyClustering · Noisy clustering, general instances | query complexity: O(\frac{nk\log n}{\delta^2}+\frac{k^{10}\log^2 n}{\delta^4}) -> O(\frac{n(k+\log n)}{\delta^2}+\frac{k^{8}\log^3 n}{\del | Helped |
| Apply a best-arm-identification reduction to establish a new information-theoretic lower bound | Noisy clustering · Noisy clustering, k≥2 | expected query complexity lower bound: \Omega(\frac{nk}{\delta^2}) and \Omega(\frac{n\log n}{\delta^2}) | Mixed |
Closest papers by meaning
- Query-Efficient Correlation Clustering with Noisy Oracle (NeurIPS 2024 · similarity 0.91)
- Clustering with Non-adaptive Subset Queries (NeurIPS 2024 · similarity 0.89)
- Optimal Algorithms for Learning Partitions with Faulty Oracles (NeurIPS 2024 · similarity 0.88)
- Clustering Items through Bandit Feedback: Finding the Right Feature out of Many (ICML 2025 · similarity 0.87)
- Relative Error Fair Clustering in the Weak-Strong Oracle Model (ICML 2025 · similarity 0.85)
- Oracle-Efficient Combinatorial Semi-Bandits (NeurIPS 2025 · 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.