Skip to main content

A Permutation-Equivariant Neural Network Architecture For Auction Design

Author(s): Rahme, Jad; Jelassi, Samy; Bruna, Joan; Weinberg, S. Matthew

To refer to this page use:
Abstract: Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. Theoretical approaches to the problem have hit some limits in the past decades and analytical solutions are known for only a few simple settings. Computational approaches to the problem through the use of LPs have their own set of limitations. Building on the success of deep learning, a new approach was recently proposed by Duetting et al. (2019) in which the auction is modeled by a feed-forward neural network and the design problem is framed as a learning problem. The neural architectures used in that work are general purpose and do not take advantage of any of the symmetries the problem could present, such as permutation equivariance. In this work, we consider auction design problems that have permutation-equivariant symmetry and construct a neural architecture that is capable of perfectly recovering the permutation-equivariant optimal mechanism, which we show is not possible with the previous architecture. We demonstrate that permutation-equivariant architectures are not only capable of recovering previous results, they also have better generalization properties.
Publication Date: 18-May-2021
Citation: Rahme, Jad, Jelassi, Samy, Bruna, Joan, and Weinberg, S. Matthew. "A permutation-equivariant neural network architecture for auction design." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 6 (2021): 5664-5672.
DOI: 10.1609/aaai.v35i6.16711
Pages: 5664 - 5672
Type of Material: Conference Article
Journal/Proceeding Title: Proceedings of the AAAI Conference on Artificial Intelligence
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.