Complex Trainable ISTA for Linear and Nonlinear Inverse Problems
This addresses signal recovery problems in signal processing and wireless communications, but appears incremental as it extends existing methods to complex fields.
The paper tackled complex-field signal recovery from noisy linear/nonlinear measurements by proposing C-TISTA, a trainable iterative algorithm based on deep unfolding, which showed remarkable performance compared to existing algorithms, though no concrete numbers were provided.
Complex-field signal recovery problems from noisy linear/nonlinear measurements appear in many areas of signal processing and wireless communications. In this paper, we propose a trainable iterative signal recovery algorithm named complex-field TISTA (C-TISTA) which treats complex-field nonlinear inverse problems. C-TISTA is based on the concept of deep unfolding and consists of a gradient descent step with the Wirtinger derivatives followed by a shrinkage step with a trainable complex-valued shrinkage function. Importantly, it contains a small number of trainable parameters so that its training process can be executed efficiently. Numerical results indicate that C-TISTA shows remarkable signal recovery performance compared with existing algorithms.