This paper introduces and develops coderivative-based Newton methods with Wolfe linesearch conditions to solve various classes of problems in nonsmooth optimization and machine learning. We first propose a generalized regularized Newton method with Wolfe linesearch (GRNM-W) for unconstrained $C^{1,1}$ minimization problems (which are second-order nonsmooth) and establish global as well as local superlinear convergence of their iterates. The Newton directions in the algorithm are obtained by solving linear equations extracted from coderivatives. To deal with convex composite minimization problems (which are first-order nonsmooth and can be constrained), we combine the proposed GRNM-W with two algorithmic frameworks: the forward-backward envelope and the augmented Lagrangian method resulting in the two new algorithms called CNFB and CNAL, respectively. Finally, we present numerical results to solve Lasso and support vector machine problems appearing in, e.g., machine learning and statistics, which demonstrate the efficiency of the proposed algorithms.
Article