An Expectation-Maximization Relaxed Method for Privacy Funnel
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929332991033344 |
|---|---|
| author | Chen, Lingyi Ye, Jiachuan Wu, Shitong Wu, Huihui Wu, Hao Zhang, Wenyi |
| author_facet | Chen, Lingyi Ye, Jiachuan Wu, Shitong Wu, Huihui Wu, Hao Zhang, Wenyi |
| contents | The privacy funnel (PF) gives a framework of privacy-preserving data release, where the goal is to release useful data while also limiting the exposure of associated sensitive information. This framework has garnered significant interest due to its broad applications in characterization of the privacy-utility tradeoff. Hence, there is a strong motivation to develop numerical methods with high precision and theoretical convergence guarantees. In this paper, we propose a novel relaxation variant based on Jensen's inequality of the objective function for the computation of the PF problem. This model is proved to be equivalent to the original in terms of optimal solutions and optimal values. Based on our proposed model, we develop an accurate algorithm which only involves closed-form iterations. The convergence of our algorithm is theoretically guaranteed through descent estimation and Pinsker's inequality. Numerical results demonstrate the effectiveness of our proposed algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_00616 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Expectation-Maximization Relaxed Method for Privacy Funnel Chen, Lingyi Ye, Jiachuan Wu, Shitong Wu, Huihui Wu, Hao Zhang, Wenyi Information Theory The privacy funnel (PF) gives a framework of privacy-preserving data release, where the goal is to release useful data while also limiting the exposure of associated sensitive information. This framework has garnered significant interest due to its broad applications in characterization of the privacy-utility tradeoff. Hence, there is a strong motivation to develop numerical methods with high precision and theoretical convergence guarantees. In this paper, we propose a novel relaxation variant based on Jensen's inequality of the objective function for the computation of the PF problem. This model is proved to be equivalent to the original in terms of optimal solutions and optimal values. Based on our proposed model, we develop an accurate algorithm which only involves closed-form iterations. The convergence of our algorithm is theoretically guaranteed through descent estimation and Pinsker's inequality. Numerical results demonstrate the effectiveness of our proposed algorithm. |
| title | An Expectation-Maximization Relaxed Method for Privacy Funnel |
| topic | Information Theory |
| url | https://arxiv.org/abs/2405.00616 |