Header logo is am

Kernel carpentry for onlne regression using randomly varying coefficient model

2007

Conference Paper

am


We present a Bayesian formulation of locally weighted learning (LWL) using the novel concept of a randomly varying coefficient model. Based on this, we propose a mechanism for multivariate non-linear regression using spatially localised linear models that learns completely independent of each other, uses only local information and adapts the local model complexity in a data driven fashion. We derive online updates for the model parameters based on variational Bayesian EM. The evaluation of the proposed algorithm against other state-of-the-art methods reveal the excellent, robust generalization performance beside surprisingly efficient time and space complexity properties. This paper, for the first time, brings together the computational efficiency and the adaptability of Õnon-competitiveÕ locally weighted learning schemes and the modeling guarantees of the Bayesian formulation.

Author(s): Edakunni, N. U. and Schaal, S. and Vijayakumar, S.
Book Title: Proceedings of the 20th International Joint Conference on Artificial Intelligence
Year: 2007

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

Address: Hyderabad, India: Jan. 6-12
Cross Ref: p2657
Note: clmc
URL: http://www-clmc.usc.edu/publications/E/edakunni-IJCAI2007.pdf

BibTex

@inproceedings{Edakunni_PIJCAI_2007,
  title = {Kernel carpentry for onlne regression using randomly varying coefficient model},
  author = {Edakunni, N. U. and Schaal, S. and Vijayakumar, S.},
  booktitle = {Proceedings of the 20th International Joint Conference on Artificial Intelligence},
  address = {Hyderabad, India: Jan. 6-12},
  year = {2007},
  note = {clmc},
  crossref = {p2657},
  url = {http://www-clmc.usc.edu/publications/E/edakunni-IJCAI2007.pdf}
}