Research map / Learning theory and algorithms / Matrix and tensor methods
Generalized Rank-Breaking: Computational and Statistical Tradeoffs
Ashish Khetan, Sewoong Oh
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 generalized rank-breaking instead of inconsistent pairwise rank-breaking | Plackett-Luce estimation · Simulated PL data, increasing n | MSE of weight estimate | Improved |
| increase rank-breaking order M (ablation) | Generalized rank-breaking · Simulated PL data (d=256) | MSE of weight estimate | Improved |
| increase number of hyper edges l to large values (ablation) | Generalized rank-breaking · Simulated PL data (d=512) | MSE of weight estimate | Hurt |
| increase top-set size m (large r) (ablation) | Generalized rank-breaking · Simulated PL data | MSE of weight estimate | Improved |
| increase top-set size m (small r) (ablation) | Generalized rank-breaking · Simulated PL data | MSE of weight estimate | Mixed |
| increase dynamic range b (ablation) | Generalized rank-breaking · Simulated PL data | MSE of weight estimate | Hurt |
| use generalized rank-breaking instead of pairwise rank-breaking | Generalized rank-breaking · Sushi dataset | MSE of weight estimate | Improved |
| increase top-set size m (ablation) | Generalized rank-breaking · Sushi dataset | MSE of weight estimate | Improved |
| use generalized rank-breaking instead of pairwise rank-breaking | Generalized rank-breaking · Jester dataset | MSE of weight estimate | Improved |
| increase top-set size m with fixed effective samples (ablation) | Generalized rank-breaking · Jester dataset | MSE of weight estimate | Hurt |
| increase sample size n (ablation) | Generalized rank-breaking · Jester dataset | MSE of weight estimate | Improved |
Closest papers by meaning
- Computational and Statistical Tradeoffs in Learning to Rank (NeurIPS 2016 · similarity 0.90)
- Data-driven Rank Breaking for Efficient Rank Aggregation (ICML 2016 · similarity 0.89)
- Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening (ICML 2017 · similarity 0.86)
- Rank Aggregation via Heterogeneous Thurstone Preference Models (AAAI 2020 · similarity 0.86)
- Optimal Sample Complexity of M-wise Data for Top-K Ranking (NeurIPS 2017 · similarity 0.86)
- Fast Algorithm for Generalized Multinomial Models with Ranking Data (ICML 2019 · 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.
