Learning gradients by a gradient descent algorithm

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

23 Scopus Citations
View graph of relations


Related Research Unit(s)


Original languageEnglish
Pages (from-to)1018-1027
Journal / PublicationJournal of Mathematical Analysis and Applications
Issue number2
Publication statusPublished - 15 May 2008


We propose a stochastic gradient descent algorithm for learning the gradient of a regression function from random samples of function values. This is a learning algorithm involving Mercer kernels. By a detailed analysis in reproducing kernel Hilbert spaces, we provide some error bounds to show that the gradient estimated by the algorithm converges to the true gradient, under some natural conditions on the regression function and suitable choices of the step size and regularization parameters. © 2007 Elsevier Inc. All rights reserved.

Research Area(s)

  • Error analysis, Learning algorithm, Reproducing kernel Hilbert space, Stochastic gradient descent, Variable selection