Clustering functional data sets by law
Galves, A., Najman, F. A., Svarc, M., & Vargas, C. D. (2025).
We introduce a new clustering procedure for functional data analysis which can classify independent sets of functional samples by their probabilistic law, i.e. that aims to assign data sets to the same cluster if and only if the data were generated with the same underlying distribution. This method has the virtue of being non-supervised and non-parametric, allowing for exploratory investigation with few assumptions about the data. We also present rigorous finite bounds that give us the effect of the number of samples in each dataset on the classification. We also provide an objective heuristic that consistently selects the best partition in a data-driven manner. We show the performance of the method by clustering simulated datasets generated with different distributions.
Stochastic Processes and their Applications, 104796