Title: Element-wise estimation error of a total variation regularized estimator for change point detection
Authors: Teng Zhang - University of Central Florida (United States) [presenting]
Abstract: The total variation regularized 2 estimator (fused lasso) is studied in the setting of a change point detection problem. Compared with existing works that focus on the sum of squared estimation errors, we give bound on the element-wise estimation error. The bound is nearly optimal in the sense that the sum of squared error matches the best existing result, up to a logarithmic factor. This analysis of the element-wise estimation error allows a screening method that can approximately detect all the change points. We also generalize this method to the muitivariate setting, i.e., to the problem of group fused lasso.