Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.07797 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917611742167040 |
|---|---|
| author | Fuentes, Miguel Mullins, Brett McKenna, Ryan Miklau, Gerome Sheldon, Daniel |
| author_facet | Fuentes, Miguel Mullins, Brett McKenna, Ryan Miklau, Gerome Sheldon, Daniel |
| contents | Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initializing a data generating model by pre-training on public data has shown to improve the quality of synthetic data, but this technique is not applicable when model structure is not determined a priori. We develop the mechanism jam-pgm, which expands the adaptive measurements framework to jointly select between measuring public data and private data. This technique allows for public data to be included in a graphical-model-based mechanism. We show that jam-pgm is able to outperform both publicly assisted and non publicly assisted synthetic data generation mechanisms even when the public data distribution is biased. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07797 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data Fuentes, Miguel Mullins, Brett McKenna, Ryan Miklau, Gerome Sheldon, Daniel Machine Learning Artificial Intelligence Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initializing a data generating model by pre-training on public data has shown to improve the quality of synthetic data, but this technique is not applicable when model structure is not determined a priori. We develop the mechanism jam-pgm, which expands the adaptive measurements framework to jointly select between measuring public data and private data. This technique allows for public data to be included in a graphical-model-based mechanism. We show that jam-pgm is able to outperform both publicly assisted and non publicly assisted synthetic data generation mechanisms even when the public data distribution is biased. |
| title | Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.07797 |