.png){kind=icon}
.png){kind=icon}
Return
Modified Frank-Wolfe algorithm for enhanced sparsity in support vector machine classifiers
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2018.08.049.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This work proposes a new algorithm for training a re-weighted l(2) Support Vector Machine (SVM), inspired on the re-weighted Lasso algorithm of Candes et al. and on the equivalence between Lasso and SVM shown recently by Jaggi. In particular, the margin required for each training vector is set independently, defining a new weighted SVM model. These weights are selected to be binary, and they are automatically adapted during the training of the model, resulting in a variation of the Frank-Wolfe optimization algorithm with essentially the same computational complexity as the original algorithm. As shown experimentally, this algorithm is computationally cheaper to apply since it requires less iterations to converge, and it produces models with a sparser representation in terms of support vectors and which are more stable with respect to the selection of the regularization hyper-parameter. (C) 2018 Elsevier B.V. All rights reserved.
Keywords:
Support Vector Machines
Sparsity
Frank-Wolfe
Lasso
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W