Research map / Learning theory and algorithms / Submodular and game algorithms
Exact Learning of Preference Structure: Single-peaked Preferences and Beyond
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 skewed uniform distribution U_p (p<1/2) instead of uniform for sampling votes | single-axis identification · single-peaked votes on a fixed axis | samples needed for identification | Hurt |
| Sample from random peak distribution RP instead of uniform over single-peaked votes | single-axis identification · single-peaked axis identification | samples needed for identification | Helped |
| Pairwise comparisons instead of full votes | single-axis identification · single-peaked axis identification | identifiability of the axis | Hurt |
| Equivalence queries instead of sample votes | single-axis exact learning · exact learning of single axis | number of oracle queries needed | Helped |
| Two-axis mixture where axes share exactly one leaf (vs 0 or 2 shared leaves) | identifying second axis from mixture with known first axis · mixture of uniform distributions over two axes | sample complexity: O(log(1/δ)) vs O(m log(m/δ)) | Hurt |
Closest papers by meaning
- On Recognising Nearly Single-Crossing Preferences (AAAI 2018 · similarity 0.88)
- Can We Predict the Election Outcome from Sampled Votes? (AAAI 2020 · similarity 0.88)
- How Hard Is It to Explain Preferences Using Few Boolean Attributes? (AAAI 2026 · similarity 0.88)
- Selective Preference Aggregation (ICML 2025 · similarity 0.86)
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF (ICLR 2024 · similarity 0.85)
- Preference learning made easy: Everything should be understood through win rate (ICML 2025 · 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.