Research map / Learning theory and algorithms / Clustering
Clustering with Noisy Queries
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 the adaptive information-theoretic algorithm rather than querying every pair | Query-Cluster with symmetric noisy oracle · Query-Cluster, adaptive | query complexity: O(\frac{nk\log{n}}{(1-2p)^2}) queries; lower bound \Omega(\frac{nk}{\Delta(p\|q)}) | Helped |
| Use the computationally efficient adaptive algorithm | Query-Cluster with symmetric noisy oracle · Query-Cluster, adaptive | running time: O(n\log{n}+k^6) | Helped |
| Require queries to be non-adaptive, for k=2 | Query-Cluster with symmetric noisy oracle · Query-Cluster, non-adaptive, k=2 | query complexity: O(\frac{n \log{n}}{(1-2p)^4}) | Helped |
| Increase query complexity to obtain a polynomial-time algorithm | Query-Cluster · Query-Cluster, polynomial-time adaptive algorithm | query complexity: O(\frac{nk^2}{\cH^2(p\|1-p)}) versus O(\frac{nk}{\cH^2(p\|1-p)}) | Mixed |
Closest papers by meaning
- Query-Efficient Correlation Clustering with Noisy Oracle (NeurIPS 2024 · similarity 0.91)
- Optimal Clustering with Noisy Queries via Multi-Armed Bandit (ICML 2022 · similarity 0.91)
- Query Complexity of Clustering with Side Information (NeurIPS 2017 · similarity 0.90)
- Clustering with Non-adaptive Subset Queries (NeurIPS 2024 · similarity 0.89)
- Optimal Algorithms for Learning Partitions with Faulty Oracles (NeurIPS 2024 · similarity 0.88)
- Relative Error Fair Clustering in the Weak-Strong Oracle Model (ICML 2025 · similarity 0.87)
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.