Poster
Simple and sharp analysis of k-means||
Vaclav Rozhon
Keywords: [ Unsupervised and Semi-supervised Learning ] [ Unsupervised Learning ]
Abstract:
We present a simple analysis of k-means|| (Bahmani et al., PVLDB 2012) - a distributed variant of the k-means++ algorithm (Arthur and Vassilvitskii, SODA 2007). Moreover, the bound on the number of rounds is improved from $O(\log n)$ to $O(\log n / \log\log n)$, which we show to be tight.
Chat is not available.