Robust Stackelberg Buyers in Repeated Auctions
Abstract
We consider the practical and classical setting where the seller is using an exploration stage to learn the value distributions of the bidders before running a revenue-maximizing auction in a exploitation phase. In this two-stage process, we exhibit practical, simple and robust strategies with large utility uplifts for the bidders. We quantify precisely the seller revenue against non-discounted buyers, complementing recent studies that had focused on impatient/heavily discounted buyers. We also prove the robustness of these shading strategies to sample approximation error of the seller, to bidder’s approximation error of the competition and to possible change of the mechanisms.
Cite
Text
Nedelec et al. "Robust Stackelberg Buyers in Repeated Auctions." Artificial Intelligence and Statistics, 2020.Markdown
[Nedelec et al. "Robust Stackelberg Buyers in Repeated Auctions." Artificial Intelligence and Statistics, 2020.](https://mlanthology.org/aistats/2020/nedelec2020aistats-robust/)BibTeX
@inproceedings{nedelec2020aistats-robust,
title = {{Robust Stackelberg Buyers in Repeated Auctions}},
author = {Nedelec, Thomas and Calauzenes, Clement and Perchet, Vianney and El Karoui, Noureddine},
booktitle = {Artificial Intelligence and Statistics},
year = {2020},
pages = {1342-1351},
volume = {108},
url = {https://mlanthology.org/aistats/2020/nedelec2020aistats-robust/}
}