papers AI Learner
The Github is limit! Click to go to the new site.

Optimal Auctions through Deep Learning

2019-04-01
Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, Sai Srivatsa Ravindranath

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 multi-bidder, 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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1706.03459

PDF

http://arxiv.org/pdf/1706.03459


Similar Posts

Comments