Results 21 to 30 of about 681,860 (297)
Deep Neural Networks Training by Stochastic Quasi-Newton Trust-Region Methods
Algorithms, 2023 While first-order methods are popular for solving optimization problems arising in deep learning, they come with some acute deficiencies. To overcome these shortcomings, there has been recent interest in introducing second-order information through quasi-
Mahsa Yousefi, Ángeles Martínez
doaj +1 more source
Hybrid Newton-type method for a class of semismooth equations [PDF]
, 2002 In this paper, we present a hybrid method for the solution of a class of composite semismooth equations encountered frequently in applications. The method is obtained by combining a generalized finite-difference Newton method to an inexpensive direct ...
Pieraccini, Sandra
core +1 more source
Algorithms, 2021 Gradient-based methods are popularly used in training neural networks and can be broadly categorized into first and second order methods. Second order methods have shown to have better convergence compared to first order methods, especially in solving ...
S. Indrapriyadarsini +4 more
doaj +1 more source
Fast Converging Implementation of a Region-Based Active Contour Model
Journal of Algorithms & Computational Technology, 2015 PDE-based image segmentation based on the active contour model attracts many researchers due to its high precision of edge detection and the continuity of boundaries.
Haiping Xu, Hanxiang Zheng, Meiqing Wang
doaj +1 more source
Axioms, 2018 This work studies limited memory preconditioners for linear symmetric positive definite systems of equations. Connections are established between a partial Cholesky factorization from the literature and a variant of Quasi-Newton type preconditioners ...
Benedetta Morini
doaj +1 more source
A Newton-Like Trust Region Method for Large-Scale Unconstrained Nonconvex Minimization
Abstract and Applied Analysis, 2013 We present a new Newton-like method for large-scale unconstrained nonconvex minimization. And a new straightforward limited memory quasi-Newton updating based on the modified quasi-Newton equation is deduced to construct the trust region subproblem, in ...
Yang Weiwei +3 more
doaj +1 more source
Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method
, 1974 To define a likelihood we have to specify the form of distribution of the observations, but to define a quasi-likelihood function we need only specify a relation between the mean and variance of the observations and the quasi-likelihood can then be used ...
Wedderburn, R. W. M.
core +1 more source
Learning to Optimize Quasi-Newton Methods
CoRR, 2022 Fast gradient-based optimization algorithms have become increasingly essential for the computationally efficient training of machine learning models. One technique is to multiply the gradient by a preconditioner matrix to produce a step, but it is unclear what the best preconditioner matrix is.
Isaac Liao +3 more
openaire +3 more sources
Learning regularized Gauss-Newton methods
, 2022 We consider variational networks for a class of nonlinear-ill-posed least squares inverse problems. These problems are addressed by regularized Gauss-Newton type optimization algorithms where the regularization is learned by a neural network.
Francesco Colibazzi +3 more
core
Isaac Newton: De Grecia al renacimiento [PDF]
, 2022 Notas sobre la obra e historia de Isaac Newton. Este documento, preparado para el Cursos de Contexto en Astronomía de la Universidad Nacional de Colombia sede Manizales, se basa fundamentalmente en un resumen del libro de William Rankim, “Newton para ...
Duque Escobar, Gonzalo
core