Convergence analysis of a regularized Newton method with generalized regularization terms for convex optimization problems

In this paper, we present a regularized Newton method (RNM) with generalized regularization terms for an unconstrained convex optimization problem. The generalized regularization includes the quadratic, cubic, and elastic net regularization as a special case. Therefore, the proposed method is a general framework that includes not only the classical and cubic RNMs but also a novel RNM with the elastic net. We show that the proposed RNM has the global O (k^-2) and local superlinear convergence, which are the same as those of the cubic RNM.