Learning and strongly truthful multi-task peer prediction: a variational approach

DOI10.4230/LIPICS.ITCS.2021.78MaRDI QIDQ7229367zbMATH OpenFDO

Authors Grant Schoenebeck, Fang-Yi Yu

Publication date 15 April 2026

Copyright license Creative Commons Attribution 3.0 Unported

Full work available at URL https://doi.org/10.4230/LIPICS.ITCS.2021.78

zbMATH Keywords

crowdsourcinginformation elicitation without verificationmachine learning

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites work

• Dominantly Truthful Multi-task Peer Prediction with a Constant Number of Tasks
• Equilibrium selection in information elicitation without verification via information monotonicity
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
• Generalized projections for non-negative functions
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• scientific article; zbMATH DE number 3322635 (Why is no real title available?)
• scientific article; zbMATH DE number 3200971 (Why is no real title available?)
• Markov Processes and the H-Theorem
• On Conjugate Convex Functions
• Putting peer prediction under the micro(economic)scope and making truth-telling focal
• Spectral methods meet EM: a provably optimal algorithm for crowdsourcing
• Two strongly truthful mechanisms for three heterogeneous agents answering one question

This page was built for publication: Learning and strongly truthful multi-task peer prediction: a variational approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7229367)