Optimal change-point estimation from indirect observationsCoauthor(s): Alexander Goldenshluger, A. Tsybakov.
We study nonparametric change-point estimation from indirect noisy observations. Focusing on the white noise convolution model, we consider two classes of functions that are smooth apart from the change-point. We establish lower bounds on the minimax risk in estimating the change-point and develop rate optimal estimation procedures. The results demonstrate that the best achievable rates of convergence are determined both by smoothness of the function away from the change-point and by the degree of ill-posedness of the convolution operator. Optimality is obtained by introducing a new technique that involves, as a key element, detection of zero crossings of an estimate of the properly smoothed second derivative of the underlying function.
Visit the Annals of Statistics home page.
Source: The Annals of Statistics
Goldenshluger, Alexander, A. Tsybakov, and Assaf Zeevi. "Optimal change-point estimation from indirect observations." The Annals of Statistics 34, no. 1 (February 2006): 35o-372.
Date: 2 2006