Structural risk minimization for robust blind identification of sparse SIMO channels

In this paper the structural risk minimization (SRM) principle is applied to derive an iterative algorithm for blind identification of sparse single-input multiple-output (SIMO) channels. The key idea consists of reformulating this problem as a support vector regression (SVR) problem in which the channel coefficients are the Lagrange multipliers of the dual problem. By employing the Vapnik's e-insensitivity loss function, the solution can be expanded in terms of a reduced number of Lagrange multipliers (i.e., the nonzero filter coefficients) and then a sparse solution is found. This method can be also used for non-sparse channels when the channel order has been highly overestimated. In this situation, the SRM principle pushes zero to the small leading and trailing terms of the impulse response. Some simulation results are provided to demonstrate the performance of the method.