Graph Filter Design Using Sum-of-squares Representation
Tuomas Aittomäki, Geert J. T. Leus · 2019
Graph filters are an essential part of signal processing on graphs enabling one to modify the spectral content of the graph signals. This paper proposes a graph filter optimization method with an exact control of the ripple on the passband and the stopband of the filter. The proposed filter design method is based on the sum-of-squares representation of positive polynomials. The optimization of both FIR and ARMA graph filters is convex with the proposed method.