Personalized Privacy Amplification via Importance Sampling
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917969649467392 |
|---|---|
| author | Fay, Dominik Mair, Sebastian Sjölund, Jens |
| author_facet | Fay, Dominik Mair, Sebastian Sjölund, Jens |
| contents | For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more frequently. In this paper, we examine the privacy properties of importance sampling, focusing on an individualized privacy analysis. We find that, in importance sampling, privacy is well aligned with utility but at odds with sample size. Based on this insight, we propose two approaches for constructing sampling distributions: one that optimizes the privacy-efficiency trade-off; and one based on a utility guarantee in the form of coresets. We evaluate both approaches empirically in terms of privacy, efficiency, and accuracy on the differentially private $k$-means problem. We observe that both approaches yield similar outcomes and consistently outperform uniform sampling across a wide range of data sets. Our code is available on GitHub: https://github.com/smair/personalized-privacy-amplification-via-importance-sampling |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_10187 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Personalized Privacy Amplification via Importance Sampling Fay, Dominik Mair, Sebastian Sjölund, Jens Cryptography and Security Machine Learning For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more frequently. In this paper, we examine the privacy properties of importance sampling, focusing on an individualized privacy analysis. We find that, in importance sampling, privacy is well aligned with utility but at odds with sample size. Based on this insight, we propose two approaches for constructing sampling distributions: one that optimizes the privacy-efficiency trade-off; and one based on a utility guarantee in the form of coresets. We evaluate both approaches empirically in terms of privacy, efficiency, and accuracy on the differentially private $k$-means problem. We observe that both approaches yield similar outcomes and consistently outperform uniform sampling across a wide range of data sets. Our code is available on GitHub: https://github.com/smair/personalized-privacy-amplification-via-importance-sampling |
| title | Personalized Privacy Amplification via Importance Sampling |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2307.10187 |