Exact Exponent in Optimal Rates for Crowdsourcing

Authors: Chao Gao, Yu Lu, Dengyong Zhou

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Under the classic Dawid-Skene model, we establish matching upper and lower bounds with an exact exponent m I(π) in which m is the number of workers and I(π) the average Chernoff information that characterizes the workers collective ability. Such an exact characterization of the error exponent allows us to state a precise sample size requirement m > 1 I(π) log 1 ϵ in order to achieve an ϵ misclassification error. In addition, our results imply the optimality of various EM algorithms for crowdsourcing initialized by consistent estimators. The main focus of this paper is to find the exact error exponent to better guide algorithm design and optimization.
Researcher Affiliation Collaboration Chao Gao CHAO.GAO@YALE.EDU Yale University, 24 Hillhouse Ave, New Haven, CT 06511 USA Yu Lu YU.LU@YALE.EDU Yale University, 24 Hillhouse Ave, New Haven, CT 06511 USA Dengyong Zhou DENGYONG.ZHOU@MICROSOFT.COM Microsoft Research, One Microsoft Way, Redmond, WA 98052 USA
Pseudocode No The paper describes algorithmic steps using equations (e.g., (7), (8), (10), (11), (12)) but does not include formal pseudocode blocks or sections labeled 'Algorithm'.
Open Source Code No The paper does not provide any explicit statements about making its source code publicly available, nor does it include links to a code repository.
Open Datasets No The paper is theoretical and does not describe experiments run on a specific publicly available dataset. It models a general crowdsourcing scenario.
Dataset Splits No The paper is theoretical and does not conduct experiments that require training, validation, or test dataset splits.
Hardware Specification No The paper is theoretical and does not describe experiments run on specific hardware, thus no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers that would be needed for reproducibility.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, such as hyperparameters or system-level training settings.