arxiv: 1202.5598 · v4 · pith:GKG2JCDXnew · submitted 2012-02-25 · 💻 cs.LG · stat.ML

Clustering using Max-norm Constrained Optimization

Ali Jalali , Nathan Srebro This is my paper

classification 💻 cs.LG stat.ML

keywords clusteringconvexmax-normotherapproachesbetterclustercompared

0 comments p. Extension

Add this Pith Number to your LaTeX paper

\usepackage{pith}
\pithnumber{GKG2JCDX}

Prints a linked pith:GKG2JCDX badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original 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.

This paper has not been read by Pith yet.

Clustering using Max-norm Constrained Optimization

discussion (0)