ML Anthology

Heteroscedastic Projection Based M-Estimators

Raghav Subbarao, Peter Meer
CVPR 2005 pp. 38
doi:10.1109/CVPR.2005.467 /cvpr/2005/subbarao2005cvpr-heteroscedastic/

Abstract

Robust regression methods, such as RANSAC, suffer from a sensitivity to the scale parameter used for generating the inlier-outlier dichotomy. Projection based M-estimators (pbM) offer a solution to this by reframing the regression problem in a projection pursuit framework. In this paper we modify the pbM formulation to obtain an improved pbM algorithm. Furthermore, the modified algorithm is easily generalized to handle heteroscedastic data . The superior performance of heteroscedastic pbM, as compared to simple pbM, is experimentally verified.

CVPR Semantic Scholar

Cite

Text

Subbarao and Meer. "Heteroscedastic Projection Based M-Estimators." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.467

Markdown

[Subbarao and Meer. "Heteroscedastic Projection Based M-Estimators." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/subbarao2005cvpr-heteroscedastic/) doi:10.1109/CVPR.2005.467

BibTeX

@inproceedings{subbarao2005cvpr-heteroscedastic,
  title     = {{Heteroscedastic Projection Based M-Estimators}},
  author    = {Subbarao, Raghav and Meer, Peter},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {38},
  doi       = {10.1109/CVPR.2005.467},
  url       = {https://mlanthology.org/cvpr/2005/subbarao2005cvpr-heteroscedastic/}
}