The spectral radius of a square matrix can be approximated by its "weighted" spectral norm

Abstract: In distributed optimization or Nash-equilibrium seeking over directed graphs, it is crucial to find a matrix norm under which the disagreement of individual agents' states contracts. In existing results, the matrix norm is usually defined by approximating the spectral radius of the matrix, which is possible when the matrix is real and has zero row-sums. In this brief note, we show that this technique can be applied to general square complex matrices. More specifically, we prove that the spectral radius of any complex square matrix can be approximated by its "weighted" spectral norm to an arbitrary degree of accuracy.