An Analysis of $D^α$ seeding for $k$-means
This provides a rigorous theoretical explanation for an observed experimental phenomenon in clustering algorithms, which is incremental but addresses a specific gap in understanding for researchers in machine learning and data analysis.
The paper tackles the problem of understanding why using D^α seeding with α>2 can improve k-means clustering results, showing that it guarantees an approximation factor with respect to the standard k-means cost, and provides experimental confirmation of this advantage.
One of the most popular clustering algorithms is the celebrated $D^α$ seeding algorithm (also know as $k$-means++ when $α=2$) by Arthur and Vassilvitskii (2007), who showed that it guarantees in expectation an $O(2^{2α}\cdot \log k)$-approximate solution to the ($k$,$α$)-means cost (where euclidean distances are raised to the power $α$) for any $α\ge 1$. More recently, Balcan, Dick, and White (2018) observed experimentally that using $D^α$ seeding with $α>2$ can lead to a better solution with respect to the standard $k$-means objective (i.e. the $(k,2)$-means cost). In this paper, we provide a rigorous understanding of this phenomenon. For any $α>2$, we show that $D^α$ seeding guarantees in expectation an approximation factor of $$ O_α\left((g_α)^{2/α}\cdot \left(\frac{σ_{\mathrm{max}}}{σ_{\mathrm{min}}}\right)^{2-4/α}\cdot (\min\{\ell,\log k\})^{2/α}\right)$$ with respect to the standard $k$-means cost of any underlying clustering; where $g_α$ is a parameter capturing the concentration of the points in each cluster, $σ_{\mathrm{max}}$ and $σ_{\mathrm{min}}$ are the maximum and minimum standard deviation of the clusters around their means, and $\ell$ is the number of distinct mixing weights in the underlying clustering (after rounding them to the nearest power of $2$). We complement these results by some lower bounds showing that the dependency on $g_α$ and $σ_{\mathrm{max}}/σ_{\mathrm{min}}$ is tight. Finally, we provide an experimental confirmation of the effects of the aforementioned parameters when using $D^α$ seeding. Further, we corroborate the observation that $α>2$ can indeed improve the $k$-means cost compared to $D^2$ seeding, and that this advantage remains even if we run Lloyd's algorithm after the seeding.