ML Anthology

Improving Random Projections Using Marginal Information

Ping Li, Trevor Hastie, Kenneth Ward Church
COLT 2006 pp. 635-649
doi:10.1007/11776420_46 /colt/2006/li2006colt-improving/

Abstract

We present an improved version of random projections that takes advantage of marginal norms. Using a maximum likelihood estimator (MLE), margin-constrained random projections can improve estimation accuracy considerably. Theoretical properties of this estimator are analyzed in detail.

PDF COLT Semantic Scholar

Cite

Text

Li et al. "Improving Random Projections Using Marginal Information." Annual Conference on Computational Learning Theory, 2006. doi:10.1007/11776420_46

Markdown

[Li et al. "Improving Random Projections Using Marginal Information." Annual Conference on Computational Learning Theory, 2006.](https://mlanthology.org/colt/2006/li2006colt-improving/) doi:10.1007/11776420_46

BibTeX

@inproceedings{li2006colt-improving,
  title     = {{Improving Random Projections Using Marginal Information}},
  author    = {Li, Ping and Hastie, Trevor and Church, Kenneth Ward},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2006},
  pages     = {635-649},
  doi       = {10.1007/11776420_46},
  url       = {https://mlanthology.org/colt/2006/li2006colt-improving/}
}