Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

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

Authors: Marius Potfer, Vianney Perchet

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical 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 Θ( T) and Θ(T 2/3), respectively. However, analysis beyond worst-case regret reveals structural differences: uniform-price auctions may admit faster learning rates, with regret scaling as Θ( T) in settings where discriminatory auctions remain at Θ(T 2/3). 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.
Researcher Affiliation Collaboration Marius Potfer1,2 Vianney Perchet1,3 1 Crest (Fairplay joint team), ENSAE 2 EDF R&D 3 Criteo AI Lab
Pseudocode Yes Algorithm 1: Full-information feedback Algorithm 2: Estimate then commit for uniform price auction Algorithm 3: Bandit Feedback Algorithm 4: Interval Refinement Algorithm 5: UBIID algorithm
Open Source Code No The paper does not include experiments.
Open Datasets No The paper does not include experiments.
Dataset Splits No The paper does not include experiments.
Hardware Specification No The paper does not include experiments.
Software Dependencies No The paper does not include experiments.
Experiment Setup No The paper does not include experiments.