Stability analysis of gradient-based neural networks for optimization problems
The authors consider for the unconstrained optimization problem \[ \min E(x), \quad x\in \mathbb{R}^n. \] A neural network model consists of the general gradient-based motion equation \[ {dx(t)\over dt}=Hg \bigl(x(t) \bigr), \quad x(t_0)= x_0\in \mathbb{R}^n \] where \(g(x)\) is the gradient of \(E(x)\), \(x_0\in \mathbb{R}^n\) is an arbitrary initial point and \(H\) is a symmetric positive definite matrix which can be viewed as a scaling matrix. The authors introduce a new approach to analyze the stability of neural network models without using any Lyapunov function.
- Combining trust-region techniques and Rosenbrock methods to compute stationary points
- The brain-state-in-a-box neural model is a gradient descent algorithm
- A time-delay neural network model for unconstrained nonconvex optimization
- A novel gradient-based neural network for solving convex second-order cone constrained variational inequality problems
- A novel neural network for solving semidefinite programming problems with some applications
- A novel neural network model for solving a class of nonlinear semidefinite programming problems
- Neurodynamical optimization
- A continuous method for convex programming problems
- A gradient-based continuous method for large-scale optimization problems
- An optimization neural network model with time-dependent and lossy dynamics
- A neurodynamic approach to zero-one quadratic programming
- A neural network based on the generalized Fischer-Burmeister function for nonlinear complementarity problems
- Neural network for solving SOCQP and SOCCVI based on two discrete-type classes of SOC complementarity functions
- A continuous method model for solving general variational inequality
- Zeroing dynamics, gradient dynamics, and Newton iterations
- Neural networks for solving second-order cone constrained variational inequality problem
- scientific article; zbMATH DE number 2079461 (Why is no real title available?)
- A Novel Neural Network for a Class of Convex Quadratic Minimax Problems
- Convergence analysis of the Levenberg–Marquardt method
- A neural network method for solving a system of linear variational inequalities
- A smoothed NR neural network for solving nonlinear convex programs with second-order cone constraints
This page was built for publication: Stability analysis of gradient-based neural networks for optimization problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5942314)
