@techreport{5102,
  title = {Sparse Multiscale Gaussian Process Regression},
  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. Although we focus on g.p. regression, the central idea is applicable to all kernel
  based algorithms, such as the support vector machine. 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. Our approach outperforms the other methods, particularly for the case of very few basis
  functions, i.e. a very high sparsity ratio.},
  number = {162},
  organization = {Max-Planck-Gesellschaft},
  institution = {Max Planck Institute for Biological Cybernetics, Tübingen, Germany},
  school = {Biologische Kybernetik},
  month = aug,
  year = {2007},
  slug = {5102},
  author = {Walder, C. and Kim, KI. and Sch{\"o}lkopf, B.},
  month_numeric = {8}
}