CMStatistics 2018: Start Registration
View Submission - CMStatistics
B1547
Title: Early stopping rules reproducing kernel Hilbert spaces Authors:  Alain Celisse - Lille University (France) [presenting]
Abstract: The main focus is on the nonparametric estimation of a regression function by means of reproducing kernels and iterative learning algorithms (gradient descent or Tikhonov regularization). First, we exploit the general framework of filter estimators to provide a unified analysis of these different algorithms. Second, we introduce an early stopping rule derived from the so-called discrepancy principle. Its behavior is compared with that one of other existing stopping rules and analyzed. An oracle type inequality is derived to quantify the finite sample performance of the proposed stopping rule. The practical performance of the procedure is also empirically assessed from simulation experiments.