8 search results - page 1 / 2 » Lower Bounds on the VC-Dimension of Smoothly Parametrized Fu... |
COLT
1994
Springer
13 years 8 months ago
1994
Springer
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
CDC
2010
IEEE
12 years 11 months ago
2010
IEEE
We derive lower bounds on the convergence speed of a widely used class of distributed averaging algorithms. In particular, we prove that any distributed averaging algorithm whose ...
JC
2007
13 years 4 months ago
2007
We construct simple algorithms for high-dimensional numerical integration of function classes with moderate smoothness. These classes consist of square-integrable functions over t...
CDC
2009
IEEE
13 years 8 months ago
2009
IEEE
This paper adresses the variance quantification problem for system identification based on the prediction error framework. The role of input and model class selection for the auto-...
UAI
2008
13 years 6 months ago
2008
Confidence measures for the generalization error are crucial when small training samples are used to construct classifiers. A common approach is to estimate the generalization err...