ML Anthology

Frugal Coordinate Descent for Large-Scale NNLS

Vamsi K. Potluru
AAAI 2012 pp. 2451-2452
doi:10.1609/AAAI.V26I1.8432 /aaai/2012/potluru2012aaai-frugal/

Abstract

The Nonnegative Least Squares (NNLS) formulation arises in many important regression problems. We present a novel coordinate descent method which differs from previous approaches in that we do not explicitly maintain complete gradient information. Empirical evidence shows that our approach outperforms a state-of-the-art NNLS solver in computation time for calculating radiation dosage for cancer treatment problems.

PDF AAAI Semantic Scholar

Cite

Text

Potluru. "Frugal Coordinate Descent for Large-Scale NNLS." AAAI Conference on Artificial Intelligence, 2012. doi:10.1609/AAAI.V26I1.8432

Markdown

[Potluru. "Frugal Coordinate Descent for Large-Scale NNLS." AAAI Conference on Artificial Intelligence, 2012.](https://mlanthology.org/aaai/2012/potluru2012aaai-frugal/) doi:10.1609/AAAI.V26I1.8432

BibTeX

@inproceedings{potluru2012aaai-frugal,
  title     = {{Frugal Coordinate Descent for Large-Scale NNLS}},
  author    = {Potluru, Vamsi K.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2012},
  pages     = {2451-2452},
  doi       = {10.1609/AAAI.V26I1.8432},
  url       = {https://mlanthology.org/aaai/2012/potluru2012aaai-frugal/}
}