Generalization bounds for learning the kernel

By Yiming Ying, Colin Campbell. 2009

55 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the optimal estimation of probability measures in weak and strong topologies (2013, methodology): “[40, Lemma 2]—also see Proposition 10—showed that the Gaussian kernel family in Example 1 is a VC-subgraph (in fact, using the proof idea in Lemma 2 of [40] it can be easily shown that Laplacian and inverse multiquadric families are also VC-subgraphs) and therefore these kernel classes ensure ( Q )…”
A Survey on Multi-view Learning (2013, methodology): “Ying and Campbell (2009) showed that the generalization analysis of the regularized kernel learning system reduces to investigation of the suprema of the Rademacher chaos process of order two over candidate kernels, and they used metric entropy integrals and the pseudo-dimension of the set of…”
Multi-task and Lifelong Learning of Kernels (2015, methodology): “Another bound with multiplicative dependence on the pseudodimension was presented in [3], where the authors used Rademacher chaos complexity measure.”
Optimal regression rates for SVMs using Gaussian kernels (2013, background): “Other results on multi-kernel regularization schemes applied to Gaussian kernels with varying widths can be found in [23, 41, 42, 43].”
Rademacher Chaos Complexities for Learning the Kernel Problem (2010, background): “Such MKL formulations have been successfully demonstrated in combining multiple heterogeneous data sources to enhance biological inference (Lanckriet et al., 2004; Damoulas & Girolami, 2008; Ying et al., 2009).”