Active Learning from Weak and Strong Labelers

Authors: Chicheng Zhang, Kamalika Chaudhuri

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide an active learning algorithm for this setting, establish its statistical consistency, and analyze its label complexity to characterize when it can provide label savings over using the strong labeler alone.
Researcher Affiliation Academia Chicheng Zhang UC San Diego chichengzhang@ucsd.edu Kamalika Chaudhuri UC San Diego kamalika@eng.ucsd.edu
Pseudocode Yes Algorithm 1 Active Learning Algorithm from Weak and Strong Labelers, Algorithm 2 Training Algorithm for Difference Classifier
Open Source Code No The paper does not contain any statement about releasing source code or provide any links to a code repository.
Open Datasets No The paper describes a theoretical framework using abstract data distributions (U and D) but does not refer to any specific publicly available datasets, provide access links, or formal citations for data used in experiments.
Dataset Splits No The paper is theoretical and does not describe empirical experiments, therefore it does not provide specific training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers for experimental setup.
Experiment Setup No The paper is theoretical and focuses on algorithm design and theoretical analysis rather than empirical experimentation, and therefore does not provide specific experimental setup details such as hyperparameter values or training configurations.