DMCA
Conditional gradient algorithms for machine learning (2012)
| Citations: | 8 - 1 self |
BibTeX
@MISC{Harchaoui12conditionalgradient,
author = {Zaid Harchaoui and Anatoli Juditsky and Arkadi Nemirovski},
title = {Conditional gradient algorithms for machine learning },
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We consider penalized formulations of machine learning problems with regularization penalty having conic structure. For several important learning problems, state-of-the-art optimization approaches such as proximal gradient algorithms are difficult to apply and computationally expensive, preventing from using them for large-scale learning purpose. We present a conditional gradient algorithm, with theoretical guarantees, and show promising experimental results on two large-scale real-world datasets.
Keyphrases
inria grenoble proximal gradient algorithm large-scale learning purpose several important learning problem state-of-the-art optimization approach penalized formulation conditional gradient algorithm regularization penalty largescale real-world datasets promising experimental result conic structure theoretical guarantee
