Clustering Using Max-Norm Constrained Optimization

Abstract

We suggest using the max-norm as a convex surrogate constraint for clustering. We show how this yields a better exact cluster recovery guarantee than previously suggested nuclear-norm relaxation, and study the effectiveness of our method, and other related convex relaxations, compared to other clustering approaches.

Cite

Text

Jalali and Srebro. "Clustering Using Max-Norm Constrained Optimization." International Conference on Machine Learning, 2012.

Markdown

[Jalali and Srebro. "Clustering Using Max-Norm Constrained Optimization." International Conference on Machine Learning, 2012.](https://mlanthology.org/icml/2012/jalali2012icml-clustering/)

BibTeX

@inproceedings{jalali2012icml-clustering,
  title     = {{Clustering Using Max-Norm Constrained Optimization}},
  author    = {Jalali, Ali and Srebro, Nathan},
  booktitle = {International Conference on Machine Learning},
  year      = {2012},
  url       = {https://mlanthology.org/icml/2012/jalali2012icml-clustering/}
}