Research map / Learning theory and algorithms / Sample complexity
Learning the Valuations of a $k$-demand Agent
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 |
|---|---|---|---|
| Biased binary search instead of standard per-item binary search (shrinking ranges unevenly by information gain) | active elicitation of k-demand valuations · theoretical query complexity | query complexity | Helped |
| Using ERM learner for passive PAC learning | passive learning of k-demand valuations · PAC sample complexity | sample complexity factor over optimal | No clear effect |
| Increasing demand k from 5 to 25 with uniform i.i.d. prices | ERM learner · n=50, empirical error rate | error rate vs training size | No clear effect |
| Increasing number of items n from 20 to 100 with unit demand | ERM learner · k=1, empirical error rate | error rate vs training size | No clear effect |
Closest papers by meaning
- Learning Market Parameters Using Aggregate Demand Queries (AAAI 2016 · similarity 0.88)
- Learning Utilities and Equilibria in Non-Truthful Auctions (NeurIPS 2020 · similarity 0.87)
- Learning to price with resource constraints: from full information to machine-learned prices (NeurIPS 2025 · similarity 0.85)
- Learning Thresholds with Latent Values and Censored Feedback (ICLR 2024 · similarity 0.85)
- Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions (ICML 2025 · similarity 0.84)
- Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design (ICML 2025 · similarity 0.84)
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.