# Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization

arXiv: https://arxiv.org/abs/2510.19591 · HTML: https://mlsanity.com/paper/2510.19591/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [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 Theory and Algorithms for Revenue Optimization in Second-Price Auctions with Reserve](https://mlsanity.com/paper/1310.5665/) (2013)
- [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)
- [Fast Rate Learning in Stochastic First Price Bidding](https://mlsanity.com/paper/2107.01835/) (2021)
- [Efficient Algorithms for Stochastic Repeated Second-price Auctions](https://mlsanity.com/paper/2011.05072/) (2020)
- [Learning and Collusion in Multi-unit Auctions](https://mlsanity.com/paper/2305.17402/) (2023)
- [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)
- [Improved learning rates in multi-unit uniform price auctions](https://mlsanity.com/paper/2501.10181/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach](https://mlsanity.com/paper/2605.31070/) (2026)

## Abstract (arXiv)

Repeated multi-unit auctions, where a seller allocates multiple identical items over many rounds, are common mechanisms in electricity markets and treasury auctions. We compare the two predominant formats: uniform-price and discriminatory auctions, focusing on the perspective of a single bidder learning to bid against stochastic adversaries. We characterize the learning difficulty in each format, showing that the regret scales similarly for both auction formats under both full-information and bandit feedback, as tildeTheta ( √T ) and tildeTheta ( T2/3 ), respectively. However, analysis beyond worst-case regret reveals structural differences: uniform-price auctions may admit faster learning rates, with regret scaling as tildeTheta ( √T ) in settings where discriminatory auctions remain at tildeTheta ( T2/3 ). Finally, we provide a specific analysis for auctions in which the other participants are symmetric and have unit-demand, and show that in these instances, a similar regret rate separation appears.