Adversarial learning for revenue-maximizing auctions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Adversarial learning for revenue-maximizing auctions

Résumé

We introduce a new numerical framework to learn optimal bidding strategies in repeated auctions when the seller uses past bids to optimize her mechanism. Crucially, we do not assume that the bidders know what optimization mechanism is used by the seller. We recover essentially all state-of-the-art analytical results for the single-item framework derived previously in the setup where the bidder knows the optimization mechanism used by the seller and extend our approach to multi-item settings, in which no optimal shading strategies were previously known. Our approach yields substantial increases in bidder utility in all settings. Our approach also has a strong potential for practical usage since it provides a simple way to optimize bidding strategies on modern marketplaces where buyers face unknown data-driven mechanisms.

Dates et versions

hal-03089784 , version 1 (28-12-2020)

Identifiants

Citer

Thomas Nedelec, Jules Baudet, Vianney Perchet, Noureddine El Karoui. Adversarial learning for revenue-maximizing auctions. 20th International Conference on Autonomous Agents and Multiagent Systems, 2021, Londres, United Kingdom. ⟨hal-03089784⟩
91 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More