Efficient Algorithms for Stochastic Repeated Second-price Auctions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Efficient Algorithms for Stochastic Repeated Second-price Auctions

Algorithmes Efficaces pour les Enchères Répétées au Second Prix

Résumé

Developing efficient sequential bidding strategies for repeated auctions is an important practical challenge in various marketing tasks. In this setting, the bidding agent obtains information, on both the value of the item at sale and the behavior of the other bidders, only when she wins the auction. Standard bandit theory does not apply to this problem due to the presence of action-dependent censoring. In this work, we consider second-price auctions and propose novel, efficient UCB-like algorithms for this task. These algorithms are analyzed in the stochastic setting, assuming regularity of the distribution of the opponents' bids. We provide regret upper bounds that quantify the improvement over the baseline algorithm proposed in the literature. The improvement is particularly significant in cases when the value of the auctioned item is low, yielding a spectacular reduction in the order of the worst-case regret. We further provide the first parametric lower bound for this problem that applies to generic UCB-like strategies. As an alternative, we propose more explainable strategies which are reminiscent of the Explore Then Commit bandit algorithm. We provide a critical analysis of this class of strategies, showing both important advantages and limitations. In particular, we provide a minimax lower bound and propose a nearly minimax-optimal instance of this class.
Fichier principal
Vignette du fichier
achddou21.pdf (495.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02997579 , version 1 (10-11-2020)
hal-02997579 , version 2 (25-02-2021)

Licence

Paternité

Identifiants

Citer

Juliette Achddou, Olivier Cappé, Aurélien Garivier. Efficient Algorithms for Stochastic Repeated Second-price Auctions. ALT 2021 - 32nd International Conference on Algorithmic Learning Theory, Mar 2021, Paris, France. ⟨hal-02997579v2⟩
147 Consultations
395 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More