Optimal Auctions Through Deep Learning.
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 r...
| Publicado en: | Communications of the ACM Vol. 64; no. 8; pp. 109 - 117 |
|---|---|
| Autores principales: | , , , , |
| Formato: | Artículo |
| Publicado: |
Association for Computing Machinery
Aug2021
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=151620530&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 151620530 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Aug2021 vid: 64 iid: 8 pid: 68 pub: Association for Computing Machinery artinfo: ui: 151620530 10.1145/3470442 ppf: 109 ppct: 8 formats: tig: atl: Optimal Auctions Through Deep Learning. aug: au: Dütting, Paul Zhe Feng Narasimhan, Harikrishna Parkes, David C. Ravindranath, Sai S. affil: Google Research, Zürich, Switzerland School of Engineering and Applied Sciences at Harvard University, Cambridge, MA, USA Google Research, Mountain View, CA, USA Harvard University, MA, USA su: Auctions Deep learning Mathematical optimization Artificial neural networks Economics Machine learning sug: subj: Auctions Deep learning Mathematical optimization Artificial neural networks Economics Machine learning ab: 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 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. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2021 holdings: @attributes: islocal: N |
|---|