ML Anthology

Anytime Interval-Valued Outputs for Kernel Machines: Fast Support Vector Machine Classification via Distance Geometry

Dennis DeCoste
ICML 2002 pp. 99-106
/icml/2002/decoste2002icml-anytime/

Abstract

Classifying M query examples using a support vector machine containing L support vectors traditionally requires exactly M * L kernel computations. We introduce a computational geometry method for which classification cost becomes roughly proportional to each query's difficulty (e.g. distance from the discriminant hyperplane). It produces exactly the same classifications, while typically requiring vastly fewer kernel computations.

Semantic Scholar

Cite

Text

DeCoste. "Anytime Interval-Valued Outputs for Kernel Machines: Fast Support Vector Machine Classification via Distance Geometry." International Conference on Machine Learning, 2002.

Markdown

[DeCoste. "Anytime Interval-Valued Outputs for Kernel Machines: Fast Support Vector Machine Classification via Distance Geometry." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/decoste2002icml-anytime/)

BibTeX

@inproceedings{decoste2002icml-anytime,
  title     = {{Anytime Interval-Valued Outputs for Kernel Machines: Fast Support Vector Machine Classification via Distance Geometry}},
  author    = {DeCoste, Dennis},
  booktitle = {International Conference on Machine Learning},
  year      = {2002},
  pages     = {99-106},
  url       = {https://mlanthology.org/icml/2002/decoste2002icml-anytime/}
}