Relative Novelty Detection
Abstract
Novelty detection is an important tool for unsupervised data analysis. It relies on finding regions of low density within which events are then flagged as novel. By design this is dependent on the underlying measure of the space. In this paper we derive a formulation which is able to address this problem by allowing for a reference measure to be given in the form of a sample from an alternate distribution. We show that this optimization problem can be solved efficiently and that it works well in practice.
Cite
Text
Smola et al. "Relative Novelty Detection." Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009.Markdown
[Smola et al. "Relative Novelty Detection." Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009.](https://mlanthology.org/aistats/2009/smola2009aistats-relative/)BibTeX
@inproceedings{smola2009aistats-relative,
title = {{Relative Novelty Detection}},
author = {Smola, Alex and Song, Le and Teo, Choon Hui},
booktitle = {Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics},
year = {2009},
pages = {536-543},
volume = {5},
url = {https://mlanthology.org/aistats/2009/smola2009aistats-relative/}
}