CoinPress: Practical Private Mean and Covariance Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912888801722368 |
|---|---|
| author | Biswas, Sourav Dong, Yihe Kamath, Gautam Ullman, Jonathan |
| author_facet | Biswas, Sourav Dong, Yihe Kamath, Gautam Ullman, Jonathan |
| contents | We present simple differentially private estimators for the mean and covariance of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effectiveness of our algorithms both theoretically and empirically using synthetic and real-world datasets -- showing that their asymptotic error rates match the state-of-the-art theoretical bounds, and that they concretely outperform all previous methods. Specifically, previous estimators either have weak empirical accuracy at small sample sizes, perform poorly for multivariate data, or require the user to provide strong a priori estimates for the parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2006_06618 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | CoinPress: Practical Private Mean and Covariance Estimation Biswas, Sourav Dong, Yihe Kamath, Gautam Ullman, Jonathan Machine Learning Cryptography and Security Data Structures and Algorithms Information Theory Statistics Theory We present simple differentially private estimators for the mean and covariance of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effectiveness of our algorithms both theoretically and empirically using synthetic and real-world datasets -- showing that their asymptotic error rates match the state-of-the-art theoretical bounds, and that they concretely outperform all previous methods. Specifically, previous estimators either have weak empirical accuracy at small sample sizes, perform poorly for multivariate data, or require the user to provide strong a priori estimates for the parameters. |
| title | CoinPress: Practical Private Mean and Covariance Estimation |
| topic | Machine Learning Cryptography and Security Data Structures and Algorithms Information Theory Statistics Theory |
| url | https://arxiv.org/abs/2006.06618 |