A new modified BFGS method for unconstrained optimization problems
Sign Up to like & getrecommendations! Published in 2018 at "Computational and Applied Mathematics"
DOI: 10.1007/s40314-018-0620-8
Abstract: Using chain rule, we propose a modified secant equation to get a more accurate approximation of the second curvature of the objective function. Then, based on this modified secant equation we present a new BFGS… read more here.
Keywords: bfgs method; unconstrained optimization; method; optimization problems ... See more keywords
A robust multi-batch L-BFGS method for machine learning*
Sign Up to like & getrecommendations! Published in 2020 at "Optimization Methods and Software"
DOI: 10.1080/10556788.2019.1658107
Abstract: ABSTRACT This paper describes an implementation of the L-BFGS method designed to deal with two adversarial situations. The first occurs in distributed computing environments where some of the computational nodes devoted to the evaluation of… read more here.
Keywords: multi batch; batch; machine learning; bfgs method ... See more keywords
The Global Convergence of a Modified BFGS Method under Inexact Line Search for Nonconvex Functions
Sign Up to like & getrecommendations! Published in 2021 at "Mathematical Problems in Engineering"
DOI: 10.1155/2021/8342536
Abstract: Among the quasi-Newton algorithms, the BFGS method is often discussed by related scholars. However, in the case of inexact Wolfe line searches or even exact line search, the global convergence of the BFGS method for… read more here.
Keywords: bfgs method; modified bfgs; line search; global convergence ... See more keywords