Saved in:
Bibliographic Details
Main Authors: Potfer, Marius, Baudry, Dorian, Richard, Hugo, Perchet, Vianney, Wan, Cheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.10181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917895210008576
author Potfer, Marius
Baudry, Dorian
Richard, Hugo
Perchet, Vianney
Wan, Cheng
author_facet Potfer, Marius
Baudry, Dorian
Richard, Hugo
Perchet, Vianney
Wan, Cheng
contents 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 $\tilde{O}(K^{5/2}\sqrt{T})$.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10181
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improved learning rates in multi-unit uniform price auctions
Potfer, Marius
Baudry, Dorian
Richard, Hugo
Perchet, Vianney
Wan, Cheng
Computer Science and Game Theory
Machine Learning
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 $\tilde{O}(K^{5/2}\sqrt{T})$.
title Improved learning rates in multi-unit uniform price auctions
topic Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/2501.10181