A decoupled first/second-order steps technique for nonconvex nonlinear unconstrained optimization with improved complexity bounds.
Serge GrattonClément W. RoyerLuís Nunes VicentePublished in: Math. Program. (2020)
Keyphrases
- unconstrained optimization
- complexity bounds
- nonlinear optimization
- objective function
- constrained optimization
- optimization methods
- trust region
- search methods
- worst case
- penalty function
- optimization method
- optimization problems
- global optimization
- convex optimization
- starting points
- neural network
- closed form solutions
- nonlinear programming
- gradient method
- hessian matrix
- genetic algorithm