Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.13677 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916257313325056 |
|---|---|
| author | Fitzsimons, Jack Pasqualini, Agustín Freitas Pisarczyk, Robert Usynin, Dmitrii |
| author_facet | Fitzsimons, Jack Pasqualini, Agustín Freitas Pisarczyk, Robert Usynin, Dmitrii |
| contents | Often we consider machine learning models or statistical analysis methods which we endeavour to alter, by introducing a randomized mechanism, to make the model conform to a differential privacy constraint. However, certain models can often be implicitly differentially private or require significantly fewer alterations. In this work, we discuss Determinantal Point Processes (DPPs) which are dispersion models that balance recommendations based on both the popularity and the diversity of the content. We introduce DPPs, derive and discuss the alternations required for them to satisfy epsilon-Differential Privacy and provide an analysis of their sensitivity. We conclude by proposing simple alternatives to DPPs which would make them more efficient with respect to their privacy-utility trade-off. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Naturally Private Recommendations with Determinantal Point Processes Fitzsimons, Jack Pasqualini, Agustín Freitas Pisarczyk, Robert Usynin, Dmitrii Machine Learning Cryptography and Security Often we consider machine learning models or statistical analysis methods which we endeavour to alter, by introducing a randomized mechanism, to make the model conform to a differential privacy constraint. However, certain models can often be implicitly differentially private or require significantly fewer alterations. In this work, we discuss Determinantal Point Processes (DPPs) which are dispersion models that balance recommendations based on both the popularity and the diversity of the content. We introduce DPPs, derive and discuss the alternations required for them to satisfy epsilon-Differential Privacy and provide an analysis of their sensitivity. We conclude by proposing simple alternatives to DPPs which would make them more efficient with respect to their privacy-utility trade-off. |
| title | Naturally Private Recommendations with Determinantal Point Processes |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2405.13677 |