Pricing a Low-Regret Seller
Abstract
As the number of ad exchanges has grown, publishers have turned to low regret learning algorithms to decide which exchange offers the best price for their inventory. This in turn opens the following question for the exchange: how to set prices to attract as many sellers as possible and maximize revenue. In this work we formulate this precisely as a learning problem, and present algorithms showing that by simply knowing that the counterparty is using a low regret algorithm is enough for the exchange to have its own low regret learning algorithm to find the optimal price.
Cite
Text
Heidari et al. "Pricing a Low-Regret Seller." International Conference on Machine Learning, 2016.Markdown
[Heidari et al. "Pricing a Low-Regret Seller." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/heidari2016icml-pricing/)BibTeX
@inproceedings{heidari2016icml-pricing,
title = {{Pricing a Low-Regret Seller}},
author = {Heidari, Hoda and Mahdian, Mohammad and Syed, Umar and Vassilvitskii, Sergei and Yazdanbod, Sadra},
booktitle = {International Conference on Machine Learning},
year = {2016},
pages = {2559-2567},
volume = {48},
url = {https://mlanthology.org/icml/2016/heidari2016icml-pricing/}
}