A novel predefined-time neurodynamic approach for mixed variational inequality problems and applications.

In this paper, we propose a novel neurodynamic approach with predefined-time stability that offers a solution to address mixed variational inequality problems. Our approach introduces an adjustable time parameter, thereby enhancing flexibility and applicability compared to conventional fixed-time stability methods. By satisfying certain conditions, the proposed approach is capable of converging to a unique solution within a predefined-time, which sets it apart from fixed-time stability and finite-time stability approaches. Furthermore, our approach can be extended to address a wide range of mathematical optimization problems, including variational inequalities, nonlinear complementarity problems, sparse signal recovery problems, and nash equilibria seeking problems in noncooperative games. We provide numerical simulations to validate the theoretical derivation and showcase the effectiveness and feasibility of our proposed method.

A study on the optimal double parameters for steepest descent with momentum.

This letter presents the stability analysis for two steepest descent algorithms with momentum for quadratic functions. The corresponding local optimal parameters in Torii and Hagan ( 2002 ) and Zhang ( 2013 ) are extended to the global optimal parameters, that is, both the optimal learning rates and the optimal momentum factors are obtained simultaneously which make for the fastest convergence.

Semistability of steepest descent with momentum for quadratic functions.

Two steepest-descent algorithms with momentum for quadratic functions are considered. For a given learning rate, the sufficient and necessary conditions for the semistability of the steepest-descent algorithms with momentum are established. Moreover, the optimal momentum factors that generally make for the fastest convergence are obtained.

Convergence of gradient method with momentum for two-layer feedforward neural networks.

A gradient method with momentum for two-layer feedforward neural networks is considered. The learning rate is set to be a constant and the momentum factor an adaptive variable. Both the weak and strong convergence results are proved, as well as the convergence rates for the error function and for the weight. Compared to the existing convergence results, our results are more general since we do not require the error function to be quadratic.