English

Outlier-Robust Convex Segmentation

Machine Learning 2014-11-19 v2 Machine Learning

Abstract

We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness to outliers is evaluated on two real-world tasks related to speech segmentation. Our algorithms outperform baseline segmentation algorithms.

Keywords

Cite

@article{arxiv.1411.4503,
  title  = {Outlier-Robust Convex Segmentation},
  author = {Itamar Katz and Koby Crammer},
  journal= {arXiv preprint arXiv:1411.4503},
  year   = {2014}
}

Comments

* Accepted to AAAI-15, this version includes the appendix/supplementary material referenced in the AAAI-15 submission, as well as color figures * This version include some minor typos correction

R2 v1 2026-06-22T07:01:33.421Z