Clustering using Max-norm Constrained Optimization
arXiv:1202.5598v432 citations
AI Analysis
This work addresses clustering challenges for data analysis, presenting an incremental improvement over existing convex relaxation methods.
The authors tackled the problem of clustering by proposing a max-norm constraint as a convex surrogate, achieving better exact cluster recovery guarantees compared to nuclear-norm relaxation.
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.