Research map / Learning theory and algorithms / Sample complexity
Exact Exponent in Optimal Rates 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 MLE with known confusion matrices instead of majority voting | one-coin Dawid-Skene model · theory (one-coin) | error exponent | Helped |
| Plug in a consistent estimate of confusion matrices into the MLE (plug-in MLE) | Dawid-Skene MLE · theory | error exponent | No clear effect |
| Initialize EM with consistent moment-based estimators (one EM step after spectral init) | EM algorithm for crowdsourcing · theory | error exponent | Helped |
Closest papers by meaning
- A Minimax Optimal Algorithm for Crowdsourcing (NeurIPS 2017 · similarity 0.90)
- Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model (ICML 2018 · similarity 0.90)
- Optimality of Belief Propagation for Crowdsourced Classification (ICML 2016 · similarity 0.89)
- Exploiting Worker Correlation for Label Aggregation in Crowdsourcing (ICML 2019 · similarity 0.88)
- Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms (NeurIPS 2019 · similarity 0.88)
- HodgeRank With Information Maximization for Crowdsourced Pairwise Ranking Aggregation (AAAI 2018 · 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.