공동 광고 판매 문제에서 수익을 최대화하는 인센티브 호환 메커니즘을 온라인 학습 관점에서 접근한다. 다양한 환경(확률적, 적대적, 부드러운 적대적)에서 효율적인 학습 알고리즘을 제안하고, 이에 대한 상한과 하한을 분석한다.
The authors propose a novel neural network-based mechanism, ExS-Net, that achieves a desirable trade-off between social welfare maximization and approximate incentive compatibility in a payment-free resource allocation setting.
Optimierung von Gerechtigkeit und Gleichheit in wiederholten gewichteten Stauungsspielen durch künstliche Währungsanreize.
Online mechanism design with predictions aims to optimize revenue through a strategyproof mechanism.
The authors propose a mechanism that combines preferences and predictions for public project decision-making, ensuring robustness to manipulation.