## KKT condition-based smoothing recurrent neural network for nonsmooth nonconvex optimization in compressed sensing

- Dan Wang, Zhuhong Zhang
- Neural Computing and Applications
- 2017

Highly Influenced

@article{Bian2014NeuralNF, title={Neural Network for Nonsmooth, Nonconvex Constrained Minimization Via Smooth Approximation}, author={Wei Bian and Xiaojun Chen}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2014}, volume={25}, pages={545-556} }

- Published 2014 in IEEE Transactions on Neural Networks and Learning…
DOI:10.1109/TNNLS.2013.2278427

A neural network based on smoothing approximation is presented for a class of nonsmooth, nonconvex constrained optimization problems, where the objective function is nonsmooth and nonconvex, the equality constraint functions are linear and the inequality constraint functions are nonsmooth, convex. This approach can find a Clarke stationary point of the optimization problem by following a continuous path defined by a solution of an ordinary differential equation. The global convergence is… CONTINUE READING

12 Citations

36 References

Similar Papers