Autonomous Motion
Note: This department has relocated.

Locally weighted projection regression: An O(n) algorithm for incremental real time learning in high dimensional spaces

2000

Conference Paper

am


Locally weighted projection regression is a new algorithm that achieves nonlinear function approximation in high dimensional spaces with redundant and irrelevant input dimensions. At its core, it uses locally linear models, spanned by a small number of univariate regressions in selected directions in input space. This paper evaluates different methods of projection regression and derives a nonlinear function approximator based on them. This nonparametric local learning system i) learns rapidly with second order learning methods based on incremental training, ii) uses statistically sound stochastic cross validation to learn iii) adjusts its weighting kernels based on local information only, iv) has a computational complexity that is linear in the number of inputs, and v) can deal with a large number of - possibly redundant - inputs, as shown in evaluations with up to 50 dimensional data sets. To our knowledge, this is the first truly incremental spatially localized learning method to combine all these properties.

Author(s): Vijayakumar, S. and Schaal, S.
Book Title: Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)
Volume: 1
Pages: 288-293
Year: 2000

Department(s): Autonomous Motion
Bibtex Type: Conference Paper (inproceedings)

Address: Stanford, CA
Cross Ref: p1269
Note: clmc
URL: http://www-clmc.usc.edu/publications/V/vijayakumar-ICML2000.pdf

BibTex

@inproceedings{Vijayakumar_PSICML_2000,
  title = {Locally weighted projection regression: An  O(n) algorithm for incremental real time learning in high dimensional spaces},
  author = {Vijayakumar, S. and Schaal, S.},
  booktitle = {Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)},
  volume = {1},
  pages = {288-293},
  address = {Stanford, CA},
  year = {2000},
  note = {clmc},
  doi = {},
  crossref = {p1269},
  url = {http://www-clmc.usc.edu/publications/V/vijayakumar-ICML2000.pdf}
}