Differentially Private Machine Learning-powered Combinatorial Auction Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913353842032640 |
|---|---|
| author | Jamshidi, Arash Hosseini, Seyed Mohammad Noormousavi, Seyed Mahdi Siavoshani, Mahdi Jafari |
| author_facet | Jamshidi, Arash Hosseini, Seyed Mohammad Noormousavi, Seyed Mahdi Siavoshani, Mahdi Jafari |
| contents | We present a new approach to machine learning-powered combinatorial auctions, which is based on the principles of Differential Privacy. Our methodology guarantees that the auction mechanism is truthful, meaning that rational bidders have the incentive to reveal their true valuation functions. We achieve this by inducing truthfulness in the auction dynamics, ensuring that bidders consistently provide accurate information about their valuation functions.
Our method not only ensures truthfulness but also preserves the efficiency of the original auction. This means that if the initial auction outputs an allocation with high social welfare, our modified truthful version of the auction will also achieve high social welfare. We use techniques from Differential Privacy, such as the Exponential Mechanism, to achieve these results. Additionally, we examine the application of differential privacy in auctions across both asymptotic and non-asymptotic regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10622 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Differentially Private Machine Learning-powered Combinatorial Auction Design Jamshidi, Arash Hosseini, Seyed Mohammad Noormousavi, Seyed Mahdi Siavoshani, Mahdi Jafari Computer Science and Game Theory Information Theory We present a new approach to machine learning-powered combinatorial auctions, which is based on the principles of Differential Privacy. Our methodology guarantees that the auction mechanism is truthful, meaning that rational bidders have the incentive to reveal their true valuation functions. We achieve this by inducing truthfulness in the auction dynamics, ensuring that bidders consistently provide accurate information about their valuation functions. Our method not only ensures truthfulness but also preserves the efficiency of the original auction. This means that if the initial auction outputs an allocation with high social welfare, our modified truthful version of the auction will also achieve high social welfare. We use techniques from Differential Privacy, such as the Exponential Mechanism, to achieve these results. Additionally, we examine the application of differential privacy in auctions across both asymptotic and non-asymptotic regimes. |
| title | Differentially Private Machine Learning-powered Combinatorial Auction Design |
| topic | Computer Science and Game Theory Information Theory |
| url | https://arxiv.org/abs/2405.10622 |