Cookies?
Library Header Image
LSE Research Online LSE Library Services

Optimal auctions through deep learning

Dütting, Paul, Feng, Zhe, Narasimham, Harikrishna, Parkes, David C. and Ravindranath, Sal S (2019) Optimal auctions through deep learning. In: Chaudhuri, Kamalika and Salakhutdinov, Ruslan, (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019. Proceedings of Machine Learning Research,97. International Machine Learning Society, USA, 1706 - 1715. ISBN 9781510886988

[img] Text (Duetting_optimal-auctions-through-deep-learning--published) - Published Version
Available under License Creative Commons Attribution.

Download (889kB)
[img] Text (Duetting_optimal-auctions-through-deep-learning-appendix--published) - Published Version
Available under License Creative Commons Attribution.

Download (868kB)

Abstract

Designing an incentive compatible auction that maximizes expected revenue is an intricate task. The single-item case was resolved in a seminal piece of work by Myerson in 1981. Even after 30-40 years of intense research the problem remains unsolved for seemingly simple multibidder, multi-item settings. In this work, we initiate the exploration of the use of tools from deep learning for the automated design of optimal auctions. We model an auction as a multi-layer neural network, frame optimal auction design as a constrained learning problem, and show how it can be solved using standard pipelines. We prove generalization bounds and present extensive experiments, recovering essentially all known analytical solutions for multi-item settings, and obtaining novel mechanisms for settings in which the optimal mechanism is unknown.

Item Type: Book Section
Official URL: http://proceedings.mlr.press/v97/
Additional Information: © 2019 The Authors
Divisions: Mathematics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
JEL classification: Z - Other Special Topics > Z0 - General > Z00 - General
Date Deposited: 29 May 2019 16:09
Last Modified: 11 Sep 2020 10:54
URI: http://eprints.lse.ac.uk/id/eprint/100806

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics