Research map / Learning theory and algorithms / Sample complexity
Actively Learning Hemimetrics with Applications to Eliciting User Preferences
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 hemimetric constraints and the non-myopic QClique query policy instead of independent distance learning | LearnHM vs. IndGreedy · YelpM¹ (K=5 cluster setting) | sample complexity: about an order of magnitude smaller | Helped |
| use hemimetric constraints and QClique | LearnHM vs. baseline algorithms · YelpM² | sample complexity: by a factor of ~2 | Helped |
| add triplet-comparison side information and a low-dimensional embedding | IndGreedy-SIT · YelpM¹ | sample complexity | Mixed |
| increase the noise-rate bound toward 0.5 | LearnHM and IndGreedy · YelpM¹ and YelpM², bounded-noise setting | sample complexity | Hurt |
| use LearnHM instead of IndGreedy | LearnHM · YelpM¹ and YelpM², stochastic settings | sample complexity | Helped |
| increase ε | LearnHM, IndGreedy, and IndGreedy-SIT · YelpM¹, n=100 | sample complexity | Hurt |
Closest papers by meaning
- Active Embedding Search via Noisy Paired Comparisons (ICML 2019 · similarity 0.85)
- Adaptive Hardness Negative Sampling for Collaborative Filtering (AAAI 2024 · similarity 0.83)
- Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method (ICML 2025 · similarity 0.81)
- Active preference learning for ordering items in- and out-of-sample (NeurIPS 2024 · similarity 0.81)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.81)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.81)
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.