Skip to Main content Skip to Navigation
Conference papers

A Minimax Optimal Algorithm for Crowdsourcing

Abstract : We consider the problem of accurately estimating the reliability of workers based on noisy labels they provide, which is a fundamental question in crowdsourcing. We propose a novel lower bound on the minimax estimation error which applies to any estimation procedure. We further propose Triangular Estimation (TE), an algorithm for estimating the reliability of workers. TE has low complexity, may be implemented in a streaming setting when labels are provided by workers in real time, and does not rely on an iterative procedure. We prove that TE is minimax optimal and matches our lower bound. We conclude by assessing the performance of TE and other state-of-the-art algorithms on both synthetic and real-world data.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download
Contributor : Thomas Bonald <>
Submitted on : Friday, September 22, 2017 - 4:00:22 PM
Last modification on : Wednesday, April 8, 2020 - 3:38:30 PM
Document(s) archivé(s) le : Saturday, December 23, 2017 - 2:00:16 PM


Files produced by the author(s)


  • HAL Id : hal-01592105, version 1


Thomas Bonald, Richard Combes. A Minimax Optimal Algorithm for Crowdsourcing. Neural Information Processing Systems Conference NIPS, 2017, Los Angeles, United States. ⟨hal-01592105⟩



Record views


Files downloads