Sufficient Conditions for Uniform Stability of Regularization Algorithms
In this paper, we study the stability and generalization properties of penalized empirical-risk minimization algorithms. We propose a set of properties of the penalty term that is sufficient to ensure uniform ?-stability: we show that if the penalty function satisfies a suitable convexity property,...
Main Authors: | Poggio, Tomaso, Rosasco, Lorenzo, Wibisono, Andre |
---|---|
Other Authors: | Tomaso Poggio |
Published: |
2009
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/49868 |
Similar Items
-
Learning and Invariance in a Family of Hierarchical Kernels
by: Wibisono, Andre, et al.
Published: (2010) -
Regularization Predicts While Discovering Taxonomy
by: Mroueh, Youssef, et al.
Published: (2011) -
Symmetry Regularization
by: Anselmi, Fabio, et al.
Published: (2017) -
Generalization and Properties of the Neural Response
by: Bouvrie, Jake, et al.
Published: (2010) -
Statistical Learning: Stability is Sufficient for Generalization and Necessary and Sufficient for Consistency of Empirical Risk Minimization
by: Mukherjee, Sayan, et al.
Published: (2004)