Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2311.10927 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911986985467904 |
|---|---|
| author | Zeng, Sihan Bhatt, Sujay Kreacic, Eleonora Hassanzadeh, Parisa Koppel, Alec Ganesh, Sumitra |
| author_facet | Zeng, Sihan Bhatt, Sujay Kreacic, Eleonora Hassanzadeh, Parisa Koppel, Alec Ganesh, Sumitra |
| contents | We consider the design of mechanisms that allocate limited resources among self-interested agents using neural networks. Unlike the recent works that leverage machine learning for revenue maximization in auctions, we consider welfare maximization as the key objective in the payment-free setting. Without payment exchange, it is unclear how we can align agents' incentives to achieve the desired objectives of truthfulness and social welfare simultaneously, without resorting to approximations. Our work makes novel contributions by designing an approximate mechanism that desirably trade-off social welfare with truthfulness. Specifically, (i) we contribute a new end-to-end neural network architecture, ExS-Net, that accommodates the idea of "money-burning" for mechanism design without payments; (ii)~we provide a generalization bound that guarantees the mechanism performance when trained under finite samples; and (iii) we provide an experimental demonstration of the merits of the proposed mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_10927 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Payment-Free Resource Allocation Mechanisms Zeng, Sihan Bhatt, Sujay Kreacic, Eleonora Hassanzadeh, Parisa Koppel, Alec Ganesh, Sumitra Computer Science and Game Theory Machine Learning We consider the design of mechanisms that allocate limited resources among self-interested agents using neural networks. Unlike the recent works that leverage machine learning for revenue maximization in auctions, we consider welfare maximization as the key objective in the payment-free setting. Without payment exchange, it is unclear how we can align agents' incentives to achieve the desired objectives of truthfulness and social welfare simultaneously, without resorting to approximations. Our work makes novel contributions by designing an approximate mechanism that desirably trade-off social welfare with truthfulness. Specifically, (i) we contribute a new end-to-end neural network architecture, ExS-Net, that accommodates the idea of "money-burning" for mechanism design without payments; (ii)~we provide a generalization bound that guarantees the mechanism performance when trained under finite samples; and (iii) we provide an experimental demonstration of the merits of the proposed mechanism. |
| title | Learning Payment-Free Resource Allocation Mechanisms |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2311.10927 |