Sketch-and-solve approaches to k-means clustering by semidefinite programming

Speaker: Kaiying Xie (OSU) Dates: 2023/01/27 Abstract: We introduce a sketch-and-solve approach to speed up the Peng-Wei semidefinite relaxation of k-means clustering. When the data is appropriately separated we identify the k-means optimal clustering. Otherwise, our approach provides a high-confidence…