Clustering using Max-norm Constrained Optimization
Machine Learning
2012-04-16 v4 Machine Learning
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.
Keywords
Cite
@article{arxiv.1202.5598,
title = {Clustering using Max-norm Constrained Optimization},
author = {Ali Jalali and Nathan Srebro},
journal= {arXiv preprint arXiv:1202.5598},
year = {2012}
}