Mechanism design for public projects via neural networks

Guanhua Wang, Runqi Guo, Yuko Sakurai, Muhammad Ali Babar, Mingyu Guo

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

1 被引用数 (Scopus)

抄録

We study mechanism design for nonexcludable and excludable binary public project problems. We aim to maximize the expected number of consumers and the expected agents' welfare. For the nonexcludable public project model, we identify a sufficient condition on the prior distribution for the conservative equal costs mechanism to be the optimal strategy-proof and individually rational mechanism. For general distributions, we propose a dynamic program that solves for the optimal mechanism. For the excludable public project model, we identify a similar sufficient condition for the serial cost sharing mechanism to be optimal for 2 and 3 agents. We derive a numerical upper bound. Experiments show that for several common distributions, the serial cost sharing mechanism is close to optimality. The serial cost sharing mechanism is not optimal in general. We design better performing mechanisms via neural networks. Our approach involves several technical innovations that can be applied to mechanism design in general. We interpret the mechanisms as price-oriented rationing-free (PORF) mechanisms, which enables us to move the mechanism's complex (e.g., iterative) decision making off the neural network, to a separate simulation process.We feed the prior distribution's analytical form into the cost function to provide high-quality gradients for efficient training. We use supervision to manual mechanisms as a systematic way for initialization. Our approach of "supervision and then gradient descent"is effective for improving manual mechanisms' performances. It is also effective for fixing constraint violations for heuristic-based mechanisms that are infeasible.

本文言語英語
ホスト出版物のタイトル20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021
出版社International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
ページ1368-1376
ページ数9
ISBN(電子版)9781713832621
出版ステータス出版済み - 2021
外部発表はい
イベント20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021 - Virtual, Online
継続期間: 5 3 20215 7 2021

出版物シリーズ

名前Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
3
ISSN(印刷版)1548-8403
ISSN(電子版)1558-2914

会議

会議20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021
CityVirtual, Online
Period5/3/215/7/21

All Science Journal Classification (ASJC) codes

  • 人工知能
  • ソフトウェア
  • 制御およびシステム工学

フィンガープリント

「Mechanism design for public projects via neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル