Research map / Learning theory and algorithms / Prediction and decision losses
Axioms for Learning from Pairwise Comparisons
Ritesh Noothigattu, Dominik Peters, Ariel D Procaccia
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 |
|---|---|---|---|
| Increase number of b>c comparisons from 1 to 10 in Example 5.2 | Thurstone-Mosteller MLE · Example 5.2 dataset | pairwise majority consistency: from about 4 | Hurt |
| Use Bradley-Terry instead of Thurstone-Mosteller model | MLE aggregation · Uniform samples over cube T | PMC violation rate (%): 17.8% -> 16.6% | No clear effect |
| Combine two datasets that each rank a above c | Thurstone-Mosteller MLE · Example 6.2 | separability: -0.253 -> 1.973 | Hurt |
Closest papers by meaning
- Optimal Aggregation of Uncertain Preferences (AAAI 2016 · similarity 0.88)
- Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare (NeurIPS 2025 · similarity 0.87)
- Independence of Irrelevant Alternatives under the Lens of Pairwise Distortion (AAAI 2024 · similarity 0.86)
- Preference Learning Algorithms Do Not Learn Preference Rankings (NeurIPS 2024 · similarity 0.86)
- Generalizing while preserving monotonicity in comparison-based preference learning models (NeurIPS 2025 · similarity 0.86)
- Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice (NeurIPS 2024 · 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.
