Scalable K-Medoids via True Error Bound and Familywise Bandits

no code implementations • 27 May 2019 • Aravindakshan Babu, Saurabh Agarwal, Sudarshan Babu, Hariharan Chandrasekaran

K-Medoids(KM) is a standard clustering method, used extensively on semi-metric data. Error analyses of KM have traditionally used an in-sample notion of error, which can be far from the true error and suffer from generalization gap.

Clustering