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: | Nie, Weilin, Wang, Cheng |
---|---|
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 |
Ejemplares similares
-
Convex analysis and minimization algorithms
por: Hiriart-Urruty, Jean-Baptiste, et al.
Publicado: (1993) -
Convex optimization: algorithms and complexity
por: Bubeck, Sébastien
Publicado: (2015) -
The Proximal Alternating Minimization Algorithm for Two-Block Separable Convex Optimization Problems with Linear Constraints
por: Bitterlich, Sandy, et al.
Publicado: (2018) -
Strict convexity and complex strict convexity: theory and applications
por: Istratescu
Publicado: (1983) -
An algorithmic theory of numbers, graphs, and convexity /
por: Lovász, László, 1948-
Publicado: (1986)