Results 11 to 20 of about 8,001 (254)
Faster Stochastic Quasi-Newton Methods [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2022 Stochastic optimization methods have become a class of popular optimization tools in machine learning. Especially, stochastic gradient descent (SGD) has been widely used for machine learning problems such as training neural networks due to low per-iteration computational complexity.
Qingsong Zhang +3 more
openaire +3 more sources
Studies on modified limited-memory BFGS method in full waveform inversion
Frontiers in Earth Science, 2023 Full waveform inversion (FWI) is a non-linear optimization problem based on full-wavefield modeling to obtain quantitative information of subsurface structure by minimizing the difference between the observed seismic data and the predicted wavefield. The
Meng-Xue Dai +3 more
doaj +1 more source
On the Convergence Rate of Quasi-Newton Methods on Strongly Convex Functions with Lipschitz Gradient
Mathematics, 2023 The main results of the study of the convergence rate of quasi-Newton minimization methods were obtained under the assumption that the method operates in the region of the extremum of the function, where there is a stable quadratic representation of the ...
Vladimir Krutikov +3 more
doaj +1 more source
Enhancing Quasi-Newton Acceleration for Fluid-Structure Interaction
Mathematical and Computational Applications, 2022 We propose two enhancements of quasi-Newton methods used to accelerate coupling iterations for partitioned fluid-structure interaction. Quasi-Newton methods have been established as flexible, yet robust, efficient and accurate coupling methods of multi ...
Kyle Davis +2 more
doaj +1 more source
Quasi-Newton Methods: A New Direction [PDF]
CoRR, 2012 ICML2012
Hennig, P., Kiefel, M.
openaire +7 more sources
THE NEW RANK ONE CLASS FOR UNCONSTRAINED PROBLEMS SOLVING
Science Journal of University of Zakho, 2023 One of the most well-known methods for unconstrained problems is the quasi-Newton approach, iterative solutions. The great precision and quick convergence of the quasi-Newton methods are well recognized. In this work, the new algorithm for the symmetric
Ahmed Mustafa
doaj +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
A New Globally Convergent Self-Scaling Vm Algorithm for Convex and Nonconvex Optimization [PDF]
Kirkuk Journal of Science, 2011 In unconstrained optimization, the original quasi-Newton condition where is the difference of the gradients at two successive iterations. Li and Fukushima proposed a modified BFGS methods based on a new Quasi –Newton equation where , where is a
Abbas Y. AL-Bayati, Basim A. Hassan
doaj +1 more source
Development a Hybrid Conjugate Gradient Algorithm for Solving Unconstrained Minimization Problems [PDF]
مجلة التربية والعلم, 2018 In this paper, a new hybrid nonlinear conjugate gradient method are presented, which produce sufficient descent search direction at every iteration. This method showed globally convergent under some assumptions.
Sawsan S. Ismael, Basim A. Hassan
doaj +1 more source
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