A KL-LUCB algorithm for Large-Scale Crowdsourcing

Authors: Ervin Tanczos, Robert Nowak, Bob Mankoff

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We corroborate our theoretical results with numerical experiments based on the New Yorker Cartoon Caption Contest. and Section 5 provides experimental support for the lil-KLUCB algorithm using data from the New Yorker Caption Contest.
Researcher Affiliation Collaboration Ervin Tánczos and Robert Nowak University of Wisconsin-Madison tanczos@wisc.edu, rdnowak@wisc.edu Bob Mankoff Former Cartoon Editor of the New Yorker bmankoff@hearst.com
Pseudocode Yes 1. Initialize by sampling every arm once. 2. While LTOP(t)(TTOP(t)(t), δ/(n 1)) max i =TOP(t)Ui(Ti(t), δ) do: Sample the following two arms: TOP(t), and arg max i =TOP(t)Ui(Ti(t), δ) and update means and confidence bounds. 3. Output TOP(t)
Open Source Code No The paper states 'These data can be found at https://github.com/nextml/caption-contest-data' which refers to data, not the open-source code for the proposed methodology.
Open Datasets Yes We corroborate our theoretical results with numerical experiments based on the New Yorker Cartoon Caption Contest. and Section 5 provides experimental support for the lil-KLUCB algorithm using data from the New Yorker Caption Contest. Footnote 7: These data can be found at https://github.com/nextml/caption-contest-data
Dataset Splits No The paper does not provide specific training/test/validation dataset splits (percentages, sample counts, or citations to predefined splits) for the data used in experiments.
Hardware Specification No The paper does not provide any specific hardware details (like GPU models, CPU types, or memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes We set N = 8 and δ = 0.01 in our experiments.