Sciweavers

92 search results - page 7 / 19
» Explicit recursivity into reproducing kernel Hilbert spaces
Sort
View
NIPS
2003
14 years 11 months ago
Learning to Find Pre-Images
We consider the problem of reconstructing patterns from a feature map. Learning algorithms using kernels to operate in a reproducing kernel Hilbert space (RKHS) express their solu...
Gökhan H. Bakir, Jason Weston, Bernhard Sch&o...
DIS
2007
Springer
15 years 4 months ago
A Hilbert Space Embedding for Distributions
We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a reprodu...
Alexander J. Smola, Arthur Gretton, Le Song, Bernh...
FOCM
2006
50views more  FOCM 2006»
14 years 9 months ago
Online Learning Algorithms
In this paper, we study an online learning algorithm in Reproducing Kernel Hilbert Spaces (RKHS) and general Hilbert spaces. We present a general form of the stochastic gradient m...
Steve Smale, Yuan Yao
JMLR
2010
118views more  JMLR 2010»
14 years 4 months ago
Hilbert Space Embeddings and Metrics on Probability Measures
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing, and independence testing....
Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fu...
JMLR
2007
104views more  JMLR 2007»
14 years 9 months ago
Learnability of Gaussians with Flexible Variances
Gaussian kernels with flexible variances provide a rich family of Mercer kernels for learning algorithms. We show that the union of the unit balls of reproducing kernel Hilbert s...
Yiming Ying, Ding-Xuan Zhou