Full Convergence of Regularized Methods for Unconstrained Optimization

Typically, the sequence of points generated by an optimization algorithm may have multiple limit points. Under convexity assumptions, however, (sub)gradient methods are known to generate a convergent sequence of points. In this paper, we extend the latter property to a broader class of algorithms. Specifically, we study unconstrained optimization methods that use local quadratic models regularized by a power [Formula: see text] of the norm of the step. In particular, we focus on the case in which only the objective function and its gradient are evaluated. Our analysis shows that, by a careful choice of the regularized model at every iteration, the whole sequence of points generated by this class of algorithms converges if the objective function is pseudo-convex. The result is achieved by employing appropriate matrices to ensure that the sequence of points is variable metric quasi-Fejér monotone.