/* ---- Google Analytics Code Below */

Tuesday, July 27, 2021

Designing Optimal Auctions Through DeepLearning

Long time involved in auction protocols.  So this interested me.  Not quite sure how it would work in contexts, but intriguing.  Technical.

Optimal Auctions Through Deep Learning  By Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, Sai S. Ravindranath

Communications of the ACM, August 2021, Vol. 64 No. 8, Pages 109-116  10.1145/3470442

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 settings with two or more items. We overview recent research results that show how tools from deep learning are shaping up to become a powerful tool for the automated design of near-optimal auctions. In this approach, an auction is modeled as a multilayer neural network, with optimal auction design framed as a constrained learning problem that can be addressed with standard machine learning pipelines. Through this approach, it is possible to recover to a high degree of accuracy essentially all known analytically derived solutions for multi-item settings and obtain novel mechanisms for settings in which the optimal mechanism is unknown.  ... " 

No comments: