Adaptive Support Vector Machine for Time-Varying Data Streams Using Martingale

Abstract

A martingale framework is proposed to enable support vector machine (SVM) to adapt to timevarying data streams. The adaptive SVM is a onepass incremental algorithm that (i) does not require a sliding window on the data stream, (ii) does not require monitoring the performance of the classifier as data points are streaming, and (iii) works well for high dimensional, multi-class data streams. Our experiments show that the novel adaptive SVM is effective at handling time-varying data streams simulated using both a synthetic dataset and a multiclass real dataset.

Cite

Text

Ho and Wechsler. "Adaptive Support Vector Machine for Time-Varying Data Streams Using Martingale." International Joint Conference on Artificial Intelligence, 2005.

Markdown

[Ho and Wechsler. "Adaptive Support Vector Machine for Time-Varying Data Streams Using Martingale." International Joint Conference on Artificial Intelligence, 2005.](https://mlanthology.org/ijcai/2005/ho2005ijcai-adaptive/)

BibTeX

@inproceedings{ho2005ijcai-adaptive,
  title     = {{Adaptive Support Vector Machine for Time-Varying Data Streams Using Martingale}},
  author    = {Ho, Shen-Shyang and Wechsler, Harry},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2005},
  pages     = {1606-1607},
  url       = {https://mlanthology.org/ijcai/2005/ho2005ijcai-adaptive/}
}