Auction learning as a two-player game

06/10/2020
by   Jad Rahme, et al.
0

Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. While theoretical approaches to the problem have hit some limits, a recent research direction initiated by Duetting et al. (2019) consists in building neural network architectures to find optimal auctions. We propose two conceptual deviations from their approach which result in enhanced performance. First, we use recent results in theoretical auction design (Rubinstein and Weinberg, 2018) to introduce a time-independent Lagrangian. This not only circumvents the need for an expensive hyper-parameter search (as in prior work), but also provides a principled metric to compare the performance of two auctions (absent from prior work). Second, the optimization procedure in previous work uses an inner maximization loop to compute optimal misreports. We amortize this process through the introduction of an additional neural network. We demonstrate the effectiveness of our approach by learning competitive or strictly improved auctions compared to prior work. Both results together further imply a novel formulation of Auction Design as a two-player game with stationary utility functions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2020

A Permutation-Equivariant Neural Network Architecture For Auction Design

Designing an incentive compatible auction that maximizes expected revenu...
research
08/17/2023

RTB Formulation Using Point Process

We propose a general stochastic framework for modelling repeated auction...
research
01/29/2022

A Context-Integrated Transformer-Based Neural Network for Auction Design

One of the central problems in auction design is developing an incentive...
research
08/19/2022

Myerson on a Network

The auction of a single indivisible item is one of the most celebrated p...
research
04/22/2022

Auction Design in an Auto-bidding Setting: Randomization Improves Efficiency Beyond VCG

Auto-bidding is an area of increasing importance in the domain of online...
research
02/20/2020

Heavy Tails Make Happy Buyers

In a second-price auction with i.i.d. (independent identically distribut...
research
10/06/2022

Learning Algorithms for Intelligent Agents and Mechanisms

In this thesis, we research learning algorithms for optimal decision mak...

Please sign up or login with your details

Forgot password? Click here to reset