Date(s) : 11/10/2013 iCal
14 h 00 min - 15 h 00 min
Inverse Statistical Learning : From minimax to algorithm\n\nBy Sébastien Loustau\, LAREMA\, Univ. Angers.\n\nWe propose to consider the problem of statistical learning when we observe a contaminated sample. More precisely\, we state minimax rates of convergence in classification with errors in variables for deconvolution empirical risk minimizers. These fast rates depends on the ill-posedness\, the margin and the complexity of the problem. The cornerstone of the proof is a bias variance decomposition of the excess risk.\nAfter a theoretical study of the problem\, we turn out into more practical considerations by presenting a new algorithm for noisy finite dimensional clustering called noisy K-means. The algorithm is based on a two-step procedure : a deconvolution step to deal with noisy inputs and Newton’s iteration as the popular k-means.
Catégories Pas de Catégories