Learning to bid in revenue-maximizing auctions

Thomas Nedelec, Noureddine El Karoui, Vianney Perchet
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4781-4789, 2019.

Abstract

We consider the problem of the optimization of bidding strategies in prior-dependent revenue-maximizing auctions, when the seller fixes the reserve prices based on the bid distributions. Our study is done in the setting where one bidder is strategic. Using a variational approach, we study the complexity of the original objective and we introduce a relaxation of the objective functional in order to use gradient descent methods. Our approach is simple, general and can be applied to various value distributions and revenue-maximizing mechanisms. The new strategies we derive yield massive uplifts compared to the traditional truthfully bidding strategy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-nedelec19a, title = {Learning to bid in revenue-maximizing auctions}, author = {Nedelec, Thomas and Karoui, Noureddine El and Perchet, Vianney}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {4781--4789}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/nedelec19a/nedelec19a.pdf}, url = {https://proceedings.mlr.press/v97/nedelec19a.html}, abstract = {We consider the problem of the optimization of bidding strategies in prior-dependent revenue-maximizing auctions, when the seller fixes the reserve prices based on the bid distributions. Our study is done in the setting where one bidder is strategic. Using a variational approach, we study the complexity of the original objective and we introduce a relaxation of the objective functional in order to use gradient descent methods. Our approach is simple, general and can be applied to various value distributions and revenue-maximizing mechanisms. The new strategies we derive yield massive uplifts compared to the traditional truthfully bidding strategy.} }
Endnote
%0 Conference Paper %T Learning to bid in revenue-maximizing auctions %A Thomas Nedelec %A Noureddine El Karoui %A Vianney Perchet %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-nedelec19a %I PMLR %P 4781--4789 %U https://proceedings.mlr.press/v97/nedelec19a.html %V 97 %X We consider the problem of the optimization of bidding strategies in prior-dependent revenue-maximizing auctions, when the seller fixes the reserve prices based on the bid distributions. Our study is done in the setting where one bidder is strategic. Using a variational approach, we study the complexity of the original objective and we introduce a relaxation of the objective functional in order to use gradient descent methods. Our approach is simple, general and can be applied to various value distributions and revenue-maximizing mechanisms. The new strategies we derive yield massive uplifts compared to the traditional truthfully bidding strategy.
APA
Nedelec, T., Karoui, N.E. & Perchet, V.. (2019). Learning to bid in revenue-maximizing auctions. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:4781-4789 Available from https://proceedings.mlr.press/v97/nedelec19a.html.

Related Material