Multiplicative parameters in gradient descent methods | Zendy

Predrag S. Stanimirović | Zendy; Marko Miladinović | Zendy; Snežana Djordjević | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Multiplicative parameters in gradient descent methods

Author(s) -

Predrag S. Stanimirović,

Marko Miladinović,

Snežana Djordjević

Publication year - 2009

Publication title -

filomat

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.449

H-Index - 34

eISSN - 2406-0933

pISSN - 0354-5180

DOI - 10.2298/fil0903023s

Subject(s) - mathematics , hessian matrix , gradient descent , line search , descent (aeronautics) , descent direction , diagonal , backtracking , multiplicative function , gradient method , quasi newton method , mathematical optimization , newton's method in optimization , line (geometry) , algorithm , nonlinear conjugate gradient method , diagonal matrix , newton's method , iterative method , mathematical analysis , local convergence , computer science , geometry , artificial intelligence , path (computing) , aerospace engineering , engineering , quantum mechanics , artificial neural network , physics , nonlinear system , programming language

We introduced an algorithm for unconstrained optimization based on the reduction of the modified Newton method with line search into a gradient descent method. Main idea used in the algorithm construction is approximation of Hessian by a diagonal matrix. The step length calculation algorithm is based on the Taylor's development in two successive iterative points and the backtracking line search procedure.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research