Hugging Face Trending Papers

An interpretable Good--Turing restart criterion for k-means++

Read the original on Hugging Face Trending Papers →

The k-means++ algorithm is commonly restarted multiple times to avoid poor local optima, yet the number of restarts is almost always chosen arbitrarily and applied uniformly regardless of data set difficulty. This undermines any comparison relying on such a choice and wastes computation on easy data sets while potentially under-serving hard ones.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Jul 10

An interpretable Good--Turing restart criterion for k-means++

arXiv:2607. 08243v1 Announce Type: new Abstract: The k-means++ algorithm is commonly restarted multiple times to avoid poor local optima, yet the number of restarts is almost always chosen arbitrarily and applied uniformly regardless of data set difficulty.

By Renato Cordeiro de Amorim
arXiv Machine Learning
Jul 30

Randomizing the Number of Centers in k-means++

arXiv:2607. 26202v1 Announce Type: cross Abstract: The $k$-means++ algorithm is a standard and widely used seeding method for $k$-means clustering, but for a fixed number $k$ of centers its worst-case expected approximation ratio is $\Theta(\log k)$.

By Vaclav Rozhon
arXiv Machine Learning
Jul 20

Data-Native Global Optimization for Big Data K-means Clustering

arXiv:2607. 15835v1 Announce Type: new Abstract: Big data clustering remains challenging: the Minimum Sum-of-Squares Clustering (MSSC) problem underlying K-means is NP-hard, and existing methods either reach poor local minima or require prohibitive metaheuristic hybrids.

By Ravil Mussabayev, Rustam Mussabayev, Zukhra Yerdaliyeva, Kuldeyev Nursultan