Research map / Learning theory and algorithms / Sample complexity
Optimal Sample Complexity of M-wise Data for Top-K Ranking
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 |
|---|---|---|---|
| Adding a spectral method (Rank Centrality) with M-wise-to-pairwise sample breaking in the dense regime p ~ sqrt(log n / n) | Rank Centrality on pairwise data · Synthetic, n=500, K=10, Delta_K=0.1 | success rate / l-inf error | No clear effect |
| Using a sparse regime (p=0.025) instead of dense regime for Rank Centrality (ablation) | Rank Centrality · Synthetic, n=500, K=10, Delta_K=0.1 | success rate vs Spectral MLE | Hurt |
| Sample breaking to pairwise data plus Rank Centrality vs. counting and least square on M-wise data | M-wise comparison data (M=4) · Synthetic, n=100, K=5, Delta_K=0.3 | success rate | Helped |
| Increasing M (size of hyper-edges) from 3 to 15 | M-wise sampling for Rank Centrality · Synthetic, n=100, K=5, Delta_K=0.3 | empirical minimal sample complexity | Helped |
| Using real-world League of Legends data with sample breaking and Rank Centrality | Rank Centrality · League of Legends top-5 users, normalized overlap | normalized overlap vs fraction of samples | Helped |
Closest papers by meaning
- Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons (NeurIPS 2021 · similarity 0.90)
- On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons (NeurIPS 2019 · similarity 0.89)
- Ranking Distributions based on Noisy Sorting (ICML 2018 · similarity 0.89)
- Generalized Top-k Mallows Model for Ranked Choices (NeurIPS 2025 · similarity 0.87)
- Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity (ICML 2025 · similarity 0.87)
- Beyond Kemeny Medians: Consensus Ranking Distributions. Definition, Properties and Statistical Learning (NeurIPS 2026 · 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.