Clustering Stable Instances of Euclidean k-means
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), pp. 6500-6509, 2017.
The Euclidean k-means problem is arguably the most widely-studied clustering problem in machine learning. While the k-means objective is NP-hard in the worst-case, practitioners have enjoyed remarkable success in applying heuristics like Lloyd's algorithm for this problem. To address this disconnect, we study the following question: what ...More
Full Text (Upload PDF)
PPT (Upload PPT)