Local Aggregative Games

Authors: Vikas Garg, Tommi Jaakkola

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments strongly corroborate the efficacy of the local aggregative and γ-aggregative games in estimating the game structure on two real voting datasets, namely, the US Supreme Court Rulings and the Congressional Votes.
Researcher Affiliation Academia Vikas K. Garg CSAIL, MIT vgarg@csail.mit.edu Tommi Jaakkola CSAIL, MIT tommi@csail.mit.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release, or mention of supplementary materials) for the source code of the methodology described.
Open Datasets Yes We obtained a binary dataset following the procedure described in [4]. and We also experimented with the Congressional Votes data [22]
Dataset Splits No The paper mentions using a "training set" (e.g., "Let S = {a1, a2, . . . , a M} be our training set"), but it does not provide specific information about training/validation/test dataset splits, percentages, or absolute sample counts needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions functions and methods (e.g., "Re LU function"), but does not specify any software dependencies with version numbers (e.g., "Python 3.8, PyTorch 1.9, and CUDA 11.1") needed for replication.
Experiment Setup Yes All the experiments described below used the following setting of values: α = 1, C = 100, and Cf = 1. C was also set to 0.01 in all settings except when the parameters of the aggregator were fixed, when we set C = 0.01 n.