Communication Dans Un Congrès Année : 2024

Improved learning rates in multi-unit uniform price auctions

Résumé

Motivated by the strategic participation of electricity producers in electricity dayahead market, we study the problem of online learning in repeated multi-unit uniform price auctions focusing on the adversarial opposing bid setting. The main contribution of this paper is the introduction of a new modeling of the bid space. Indeed, we prove that a learning algorithm leveraging the structure of this problem achieves a regret of Õ(K 4/3 T 2/3 ) under bandit feedback, improving over the bound of Õ(K 7/4 T 3/4 ) previously obtained in the literature. This improved regret rate is tight up to logarithmic terms. Inspired by electricity reserve markets, we further introduce a different feedback model under which all winning bids are revealed. This feedback interpolates between the full-information and bandit scenarios depending on the auctions' results. We prove that, under this feedback, the algorithm that we propose achieves regret Õ(K 5/2 √ T ).
Fichier principal
Vignette du fichier
Multi_unit_auctions_redac_final__Copy_-1.pdf (412.94 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04896481 , version 1 (20-01-2025)

Licence

Identifiants

  • HAL Id : hal-04896481 , version 1

Citer

Marius Potfer, Dorian Baudry, Hugo Richard, Vianney Perchet, Cheng Wang. Improved learning rates in multi-unit uniform price auctions. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (BC), Canada. ⟨hal-04896481⟩
0 Consultations
0 Téléchargements

Partager

More