Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

A Permutation-Equivariant Neural Network Architecture For Auction Design

About

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.

Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg• 2020

Related benchmarks

TaskDatasetResultRank
Optimal Auction DesignMulti-setting Auction mixture of 2x3 to 3x7 settings (test)
Revenue4.467
33
Optimal Auction Design2x5 auction setting
Revenue2.437
15
Optimal Auction Design3x10 auction setting
Revenue5.744
15
Optimal Auction Design1x2 auction setting
Revenue58.6
9
Optimal Auction Designauction setting 2x3
Revenue1.365
9
Optimal Auction Designauction setting 2x2
Revenue87.8
9
Showing 6 of 6 rows

Other info

Follow for update