Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.01837 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909396769964032 |
|---|---|
| author | Ananthakrishnan, Nivasini Bates, Stephen Jordan, Michael I. Haghtalab, Nika |
| author_facet | Ananthakrishnan, Nivasini Bates, Stephen Jordan, Michael I. Haghtalab, Nika |
| contents | Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model. We show that a principal can cope with such asymmetry via simple linear contracts that achieve 1-1/e fraction of the optimal utility. To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract. We also study linear contracts and derive the optimal utility in the more complex setting of multiple interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_01837 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Delegating Data Collection in Decentralized Machine Learning Ananthakrishnan, Nivasini Bates, Stephen Jordan, Michael I. Haghtalab, Nika Machine Learning Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two fundamental information asymmetries that arise in decentralized ML: uncertainty in the assessment of model quality and uncertainty regarding the optimal performance of any model. We show that a principal can cope with such asymmetry via simple linear contracts that achieve 1-1/e fraction of the optimal utility. To address the lack of a priori knowledge regarding the optimal performance, we give a convex program that can adaptively and efficiently compute the optimal contract. We also study linear contracts and derive the optimal utility in the more complex setting of multiple interactions. |
| title | Delegating Data Collection in Decentralized Machine Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2309.01837 |