LGMay 13, 2014
Clustering, Hamming Embedding, Generalized LSH and the Max Norm
arXiv:1405.3167v11 citations
Originality Synthesis-oriented
AI Analysis
This work addresses theoretical relationships in machine learning for researchers, but it appears incremental as it builds on prior studies like Charikar 2002.
The paper tackles the convex relaxation of clustering and Hamming embedding, particularly in asymmetric cases like co-clustering, and explores their connections to LSH and the max-norm ball, highlighting differences between symmetric and asymmetric versions.
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.