# Improved learning rates in multi-unit uniform price auctions

arXiv: https://arxiv.org/abs/2501.10181 · HTML: https://mlsanity.com/paper/2501.10181/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 17 Jan 2025.

## Builds on (most cited first, 11 of 11)

- [Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback](https://mlsanity.com/paper/1409.8428/) (2014)
- [Online learning in repeated auctions](https://mlsanity.com/paper/1511.05720/) (2015)
- [Learning to Bid Without Knowing your Value](https://mlsanity.com/paper/1711.01333/) (2017)
- [Contextual Bandits with Cross-learning](https://mlsanity.com/paper/1809.09582/) (2018)
- [Learning in repeated auctions](https://mlsanity.com/paper/2011.09365/) (2020)
- [The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations](https://mlsanity.com/paper/2307.09478/) (2023)
- [Learning and Collusion in Multi-unit Auctions](https://mlsanity.com/paper/2305.17402/) (2023)
- [No-Regret Learning from Partially Observed Data in Repeated Auctions](https://mlsanity.com/paper/1912.09905/) (2019)
- [On the Inefficiency of Standard Multi-Unit Auctions](https://mlsanity.com/paper/1303.1646/) (2013)
- [Learning in Repeated Multi-Unit Pay-As-Bid Auctions](https://mlsanity.com/paper/2307.15193/) (2023)
- [Exploring Vickrey-Clarke-Groves Mechanism for Electricity Markets](https://mlsanity.com/paper/1611.03044/) (2016)

## Built on by (most cited first, 2 of 2)

- [Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization](https://mlsanity.com/paper/2510.19591/) (2025)
- [Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach](https://mlsanity.com/paper/2605.31070/) (2026)

## Abstract (arXiv)

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 tildeO(K4/3T2/3) under bandit feedback, improving over the bound of tildeO(K7/4T3/4) 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 tildeO(K5/2√T).