Fundamental Limits of Budget-Fidelity Trade-off in Label Crowdsourcing

Authors: Farshad Lahouti, Babak Hassibi

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, a crowdsourcing problem is modeled and analyzed in an information theoretic setting. The purpose is to seek ultimate performance bounds, in terms of the CS budget (or equivalently the number of queries per item) and a CS fidelity, that one can achieve by any form of query from the workers and any inference algorithm. ... Figure 2 shows the information theoretic limit of Corollary 1 and the bound obtained in Theorem 4.
Researcher Affiliation Academia Farshad Lahouti Electrical Engineering Department, California Institute of Technology lahouti@caltech.edu Babak Hassibi Electrical Engineering Department, California Institute of Technology hassibi@caltech.edu
Pseudocode No The paper describes coding schemes and models (e.g., 'k-ary Incidence Coding'), but it does not provide any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not mention releasing any source code or provide links to a code repository.
Open Datasets No The paper models theoretical scenarios (e.g., 'N-ary discrete source B(X)', 'uniformly distributed dataset') rather than using or specifying real-world, publicly available datasets that require access information. Therefore, it does not provide access information for a public dataset.
Dataset Splits No The paper is theoretical and focuses on deriving fundamental limits and analyzing models. It does not conduct empirical experiments with real datasets, and therefore, it does not provide information about dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not involve running experiments on specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe software implementations or dependencies with version numbers.
Experiment Setup No The paper is theoretical and focuses on modeling and analysis rather than practical experiments. As such, it does not provide details about an experimental setup, hyperparameters, or system-level training settings.