@inproceedings{5121,
  title = {Sparse Multiscale Gaussian Process Regression},
  booktitle = {Proceedings of the 25th International Conference on Machine Learning},
  abstract = {Most existing sparse Gaussian process (g.p.)
  models seek computational advantages by
  basing their computations on a set of m basis
  functions that are the covariance function of
  the g.p. with one of its two inputs fixed. We
  generalise this for the case of Gaussian covariance
  function, by basing our computations on
  m Gaussian basis functions with arbitrary diagonal
  covariance matrices (or length scales).
  For a fixed number of basis functions and
  any given criteria, this additional flexibility
  permits approximations no worse and typically
  better than was previously possible.
  We perform gradient based optimisation of
  the marginal likelihood, which costs O(m2n)
  time where n is the number of data points,
  and compare the method to various other
  sparse g.p. methods. Although we focus on
  g.p. regression, the central idea is applicable
  to all kernel based algorithms, and we also
  provide some results for the support vector
  machine (s.v.m.) and kernel ridge regression
  (k.r.r.). Our approach outperforms the other
  methods, particularly for the case of very few
  basis functions, i.e. a very high sparsity ratio.},
  pages = {1112-1119},
  editors = {WW Cohen and A McCallum and S Roweis},
  publisher = {ACM Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {New York, NY, USA},
  month = jul,
  year = {2008},
  slug = {5121},
  author = {Walder, C. and Kim, KI. and Sch{\"o}lkopf, B.},
  month_numeric = {7}
}