ML Anthology

SVM Optimization: Inverse Dependence on Training Set Size

Shai Shalev-Shwartz, Nathan Srebro
ICML 2008 pp. 928-935
doi:10.1145/1390156.1390273 /icml/2008/shalevshwartz2008icml-svm/

Abstract

We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.

PDF ICML Semantic Scholar

Cite

Text

Shalev-Shwartz and Srebro. "SVM Optimization: Inverse Dependence on Training Set Size." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390273

Markdown

[Shalev-Shwartz and Srebro. "SVM Optimization: Inverse Dependence on Training Set Size." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/shalevshwartz2008icml-svm/) doi:10.1145/1390156.1390273

BibTeX

@inproceedings{shalevshwartz2008icml-svm,
  title     = {{SVM Optimization: Inverse Dependence on Training Set Size}},
  author    = {Shalev-Shwartz, Shai and Srebro, Nathan},
  booktitle = {International Conference on Machine Learning},
  year      = {2008},
  pages     = {928-935},
  doi       = {10.1145/1390156.1390273},
  url       = {https://mlanthology.org/icml/2008/shalevshwartz2008icml-svm/}
}