Improved learning rates in multi-unit uniform price auctions
This work provides improved learning rates for participants in multi-unit uniform price auctions, particularly relevant for strategic bidding in electricity markets.
This paper addresses online learning in multi-unit uniform price auctions, motivated by electricity markets. By introducing a new bid space model, the authors achieve a regret bound of O(K^(4/3)T^(2/3)) under bandit feedback, improving upon the previous O(K^(7/4)T^(3/4)). They also propose a new feedback model inspired by electricity reserve markets, achieving a regret of O(K^(5/2)sqrt(T)).
Motivated by the strategic participation of electricity producers in electricity day-ahead 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 $\tilde{O}(K^{4/3}T^{2/3})$ under bandit feedback, improving over the bound of $\tilde{O}(K^{7/4}T^{3/4})$ 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 $\tilde{O}(K^{5/2}\sqrt{T})$.