Non-linear in-band interference cancellation on base of conjugate gradients method

TL;DR

This paper proposes a conjugate gradient method based on the mixed Newton approach for efficient nonlinear self-interference cancellation in full-duplex communication systems, balancing convergence speed and computational cost.

Contribution

It introduces a novel conjugate gradient algorithm leveraging mixed second-order derivatives to improve SIC in IBFD systems with reduced computational complexity.

Findings

Higher convergence rate than first-order methods

Lower computational resources than second-order methods

Effective nonlinear SIC in full-duplex systems

Abstract

This paper investigates one possible solution to the problem of self-interference cancellation (SIC) arising in the design of in-band full-duplex (IBFD) communication systems. Self-interference cancellation is performed in the digital domain using multilayer nonlinear models adapted via gradient-based optimization. The presence of local minima and saddle points during the adaptation of multilayer models limits the direct use of second-order methods due to the indefiniteness of the hessian matrix. The mixed Newton method can address the saddle-point issue; however, it requires significant computational resources. In this work, a conjugate gradient (CG) method constructed on the base of the mixed Newton method (MNM) is proposed. The method exploits information from mixed second-order derivatives of the loss function without explicit computation the full hessian matrix. As a result, the proposed approach achieves a higher convergence rate than first-order methods while requiring significantly lower computational resources than conventional second-order methods when adapting multilayer nonlinear self-interference cancellers in full-duplex communication systems.