A Minimax Optimal Algorithm for Crowdsourcing - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A Minimax Optimal Algorithm for Crowdsourcing

Résumé

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.
Fichier principal
Vignette du fichier
nips17.pdf (252.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01592105 , version 1 (22-09-2017)

Identifiants

  • HAL Id : hal-01592105 , version 1

Citer

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

Partager

Gmail Facebook X LinkedIn More