Title: Regularized functional subspace clustering
Authors: Yoshikazu Terada - Osaka University; RIKEN (Japan) [presenting]
Michio Yamamoto - Osaka University / RIKEN AIP (Japan)
Abstract: The intrinsic high dimensional nature of functional data often makes a possible good performance in supervised classification for functional data. Using the projection into the finite-dimensional subspace, we can extract the intrinsic high-dimensional nature from functional data. Several subspace clustering methods are proposed for functional data. However, the projected data do not necessarily reflect the hidden cluster structure in some of these methods. We propose a new regularized subspace clustering algorithm for functional data. We can ensure that the objective function monotonically decreases at each iteration for the proposed algorithm. Moreover, we study the asymptotic properties of the proposed clustering algorithm. Finally, we demonstrate that the proposed method provides better performance than the existing clustering methods for both simulated and real data through numerical experiments.