Research map / Learning theory and algorithms / Sample complexity
Maximum Selection and Ranking under Noisy Comparisons
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 a knockout tournament with round-dependent comparison confidence | Maximum selection under strong stochastic transitivity and stochastic triangle inequality · General probabilistic comparison models | comparisons: O(\frac{n}{\epsilon^2} \log \frac1{\delta}) comparisons, versus O(\frac{n}{\epsilon^2} \log \frac{n}{\epsilon \delta}) | Helped |
| Apply anchor sampling and noisy binary search around a Rank-x algorithm | Ranking under strong stochastic transitivity and stochastic triangle inequality · General probabilistic comparison models, δ ≥ 1/n | comparisons: O(\frac{n \log n (\log \log n)^x}{\epsilon^2}) | Helped |
| Use Knockout instead of BTM-PAC, MallowsMPI, or AR | Maximum selection · Simulated model p(i,j) = 0.6 for i < j; n = 7, 10, 15, 50, 100, 200, and 500 | sample complexity | Helped |
| Use Knockout instead of MallowsMPI as pairwise gaps shrink | Maximum selection · Simulated model with \tilde{p} = 0.01, 0.005, and 0.001 | sample complexity | Helped |
| Use Knockout instead of MallowsMPI as φ approaches 1 | Maximum selection · Mallows model, n = 10 | sample complexity | Helped |
| Apply Knockout to Mallows-model comparisons despite the model not satisfying the triangle inequality | Maximum selection · Mallows model, n = 10; φ = 0.99 | success rate: 10 runs out of 100 | Mixed |
Closest papers by meaning
- Maxing and Ranking with Few Assumptions (NeurIPS 2017 · similarity 0.92)
- On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons (NeurIPS 2019 · similarity 0.90)
- Active Ranking without Strong Stochastic Transitivity (NeurIPS 2022 · similarity 0.89)
- Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons (NeurIPS 2021 · similarity 0.88)
- Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity (ICML 2025 · similarity 0.88)
- Active Ranking and Matchmaking, with Perfect Matchings (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.