Skip to yearly menu bar Skip to main content


Poster

Improved learning rates in multi-unit uniform price auctions

Marius Potfer · Dorian Baudry · Hugo Richard · Vianney Perchet · Cheng Wan

West Ballroom A-D #5806
[ ]
Wed 11 Dec 11 a.m. PST — 2 p.m. PST

Abstract: 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 O~(K4/3T2/3) under bandit feedback, improving over the bound of O~(K7/4T3/4) previously obtained in the literature. This improved regret rate is tight up to logarithmic terms. %by deducing a lower bound of Ω(T2/3) from the dynamic pricing literature, proving the optimality in T of our algorithm up to log factors. 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 O~(K5/2T).

Chat is not available.