Fair Equilibria in Sponsored Search Auctions: The Advertisers’ Perspective

Authors: Georgios Birmpas, Andrea Celli, Riccardo Colini-Baldeschi, Stefano Leonardi

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we evaluate the quality of the allocations through experiments on real-world data.
Researcher Affiliation Collaboration 1Department of Computer, Control and Management Engineering, Sapienza University, Rome, Italy 2Department of Computing Sciences, Bocconi University, Milan, Italy 3Core Data Science, Meta, London, UK
Pseudocode No The paper describes algorithms such as GECE, but does not present them in structured pseudocode or clearly labeled algorithm blocks within the main text. It refers to an 'extended version of the paper' for more details on implementation.
Open Source Code No The paper does not provide concrete access to source code for the described methodology. There are no links to repositories or explicit statements about code release.
Open Datasets No We construct a real-world dataset through logs of a large Internet advertising company. The paper does not provide concrete access information (link, DOI, formal citation) for a publicly available dataset; it indicates the use of internal company logs.
Dataset Splits No The paper describes an experimental setting involving simulations over T=10^4 auctions and 20 repetitions, but it does not specify explicit training, validation, or test dataset splits.
Hardware Specification Yes Experiments are run on a 24-core machine with 57Gb of RAM.
Software Dependencies No The paper mentions using the 'EXP3 algorithm by [Auer et al., 2002]' but does not provide specific version numbers for any software dependencies or libraries used for implementation.
Experiment Setup Yes For each i, we set Vi = {x/100 : x [100] {0}}... Then, for each i Ih... we artificially set value distributions to be such that Fi(1) = 1... Quality factors are set to be γ = (1, 1).