Cargando…
Perturbation of convex risk minimization and its application in differential private learning algorithms
Convex risk minimization is a commonly used setting in learning theory. In this paper, we firstly give a perturbation analysis for such algorithms, and then we apply this result to differential private learning algorithms. Our analysis needs the objective functions to be strongly convex. This leads...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Springer International Publishing
2017
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5216179/ https://www.ncbi.nlm.nih.gov/pubmed/28133425 http://dx.doi.org/10.1186/s13660-016-1280-0 |