Learning Deep Generative Models for Queuing Systems

Authors: Cesar Ojeda, Kostadin Cvejoski, Bodgan Georgiev, Christian Bauckhage, Jannis Schuecker, Ramses J. Sanchez9214-9222

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide extensive experimental analysis on both empirical and synthetic datasets, showing the effectiveness of the proposed models.
Researcher Affiliation Collaboration 1Berlin Center for Machine Learning and TU Berlin, 10587 Berlin, Germany 2Competence Center Machine Learning Rhine-Ruhr 3Fraunhofer Center for Machine Learning and Fraunhofer IAIS, 53757 Sankt Augustin, Germany 4B-IT, University of Bonn, Bonn, Germany 5Bayer AG, Germany
Pseudocode Yes Algorithm 1: Recurrent Adversarial Service Time
Open Source Code No The paper does not provide a direct link to source code or an explicit statement that the code for the described methodology is publicly available.
Open Datasets Yes New York City Taxi Dataset (NY): ...We analyse about 1.1 10^7 trips. https://www1.nyc.gov/site/tlc/about/data-and-research.page
Dataset Splits No The paper states 'We split all datasets into training and test sets', but does not explicitly mention or detail a validation set split.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not specify software dependencies with version numbers.
Experiment Setup No Details of the neural networks architectures, learning parameters and any other hyperparameters as required in the model specification can be found in the Supplementary Material. (Not in main text)