Research map / Learning theory and algorithms / Sample complexity
A Minimax Optimal Algorithm for Crowdsourcing
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 TE instead of S-EM10 | worker-reliability estimation · Synthetic instance (iii), b=1 | estimation error: 0.389 -> 0.061 | Helped |
| Use TE instead of S-EM10 | worker-reliability estimation · Synthetic instance (i), a=0.3 | estimation error: 0.041 -> 0.134 | Hurt |
| Use TE instead of S-EM10 | worker-reliability estimation · Synthetic instance (iii), b=sqrt(n) | estimation error: 0.030 -> 0.045 | Hurt |
| Use TE rather than S-EM initialization followed by EM | binary-label worker-reliability estimation · Crowdsourcing parameter estimation | minimax estimation error | No clear effect |
| Use TE instead of S-EM10 | ground-truth prediction · Synthetic instance (iii), b=1 | prediction error: 0.404 -> 0.192 | Mixed |
| Use TE instead of majority voting | ground-truth prediction · RTE | prediction error: 0.10 -> 0.38 | Hurt |
| Use TE instead of majority voting | ground-truth prediction · Bird | prediction error: 0.24 -> 0.18 | Helped |
Closest papers by meaning
- Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model (ICML 2018 · similarity 0.91)
- Exact Exponent in Optimal Rates for Crowdsourcing (ICML 2016 · similarity 0.90)
- Optimality of Belief Propagation for Crowdsourced Classification (ICML 2016 · similarity 0.89)
- Fundamental Limits of Budget-Fidelity Trade-off in Label Crowdsourcing (NeurIPS 2016 · similarity 0.87)
- Achieving budget-optimality with adaptive schemes in crowdsourcing (NeurIPS 2016 · similarity 0.87)
- Exploiting Worker Correlation for Label Aggregation in Crowdsourcing (ICML 2019 · similarity 0.87)
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.