Clustering, Hamming Embedding, Generalized LSH and the Max Norm
Machine Learning
2014-05-14 v1
Abstract
We study the convex relaxation of clustering and hamming embedding, focusing on the asymmetric case (co-clustering and asymmetric hamming embedding), understanding their relationship to LSH as studied by (Charikar 2002) and to the max-norm ball, and the differences between their symmetric and asymmetric versions.
Cite
@article{arxiv.1405.3167,
title = {Clustering, Hamming Embedding, Generalized LSH and the Max Norm},
author = {Behnam Neyshabur and Yury Makarychev and Nathan Srebro},
journal= {arXiv preprint arXiv:1405.3167},
year = {2014}
}
Comments
17 pages