K-median Machine Learning
noun
Definition: A clustering objective and family of clustering algorithms in which one selects k centers so as to minimize the sum of distances from each data point to its nearest center; in contrast to k-means, which minimizes the sum of squared distances, k-median minimizes absolute distance and is therefore typically more robust to outliers [Costa, Farokhnejad 2025].
Example in context: “In this section, we briefly reviewed the three popular clustering approaches to be compared in the present study, including LCA, k-means, and k-medians …” [Huang et al. 2025]
Synonyms: k-median clustering; k-medians (variant label in the literature)
Related terms: k-means; k-medoids; clustering objective; metric clustering; outlier robustness; cluster center