MSE Analysis of the Projected Gradient Algorithm on Unions of Subspaces
Conference: WSA 2018 - 22nd International ITG Workshop on Smart Antennas
03/14/2018 - 03/16/2018 at Bochum, Deutschland
Proceedings: WSA 2018
Pages: 5Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Wiese, Thomas; Shibli, Kamel; Utschick, Wolfgang (Professur für Methoden der Signalverarbeitung, Technische Universität München, 80290 Munich, Germany)
Abstract:
We present a mean-squared-error (MSE) analysis of the projected gradient algorithm when applied to linear inverse problems with constraint sets that are unions of subspaces. This algorithm has been recently presented as a generalization of the iterative hard thresholding algorithm. The main difficulty with the MSE analysis is to calculate the expected value of the supremum of a continuous random process. We present a simple approach to calculate the expected supremum, which builds upon the concept of Lipschitz random processes.