English
Related papers

Related papers: Anderson Acceleration For Perturbed Newton Methods

200 papers

Anderson localization is related to exponential localization of a particle in the configuration space in the presence of a disorder potential. Anderson localization can be also observed in the momentum space and corresponds to quantum…

Atomic Physics · Physics 2017-06-07 Krzysztof Giergiel , Krzysztof Sacha

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

An iterative formula based on Newton Method alone is presented for the iterative solutions of equations that ensures convergence in cases where the traditional Newton Method may fail to converge to the desired root. In addition, the method…

Numerical Analysis · Mathematics 2012-10-30 Ababu Teklemariam Tiruneh

Alternating minimization (AM) procedures are practically efficient in many applications for solving convex and non-convex optimization problems. On the other hand, Nesterov's accelerated gradient is theoretically optimal first-order method…

Optimization and Control · Mathematics 2021-09-16 Sergey Guminov , Pavel Dvurechensky , Nazarii Tupitsa , Alexander Gasnikov

At the heart of Newton based optimization methods is a sequence of symmetric linear systems. Each consecutive system in this sequence is similar to the next, so solving them separately is a waste of computational effort. Here we describe…

Optimization and Control · Mathematics 2014-12-30 Robert Mansel Gower , Jacek Gondzio

In this paper, we propose a first second-order scheme based on arbitrary non-Euclidean norms, incorporated by Bregman distances. They are introduced directly in the Newton iterate with regularization parameter proportional to the square…

Optimization and Control · Mathematics 2021-12-07 Nikita Doikov , Yurii Nesterov

In this paper, by combining the algorithm New Q-Newton's method - developed in previous joint work of the author - with Armijo's Backtracking line search, we resolve convergence issues encountered by Newton's method (e.g. convergence to a…

Optimization and Control · Mathematics 2022-09-13 Tuyen Trung Truong

In this paper, we investigate Anderson localization for a nonlinear perturbation of the Maryland model $H=\varepsilon\Delta+\cot\pi(\theta+j\cdot\alpha)\delta_{j,j'}$ on $\mathbb{Z}^d$. Specifically, if $\varepsilon,\delta$ are sufficiently…

Analysis of PDEs · Mathematics 2025-02-26 Shihe Liu , Yunfeng Shi , Zhifei Zhang

Many modern machine learning algorithms such as generative adversarial networks (GANs) and adversarial training can be formulated as minimax optimization. Gradient descent ascent (GDA) is the most commonly used algorithm due to its…

Machine Learning · Computer Science 2022-07-01 Huan He , Shifan Zhao , Yuanzhe Xi , Joyce C Ho , Yousef Saad

Following the first part of our project, this paper comprehensively studies two types of extragradient-based methods: anchored extragradient and Nesterov's accelerated extragradient for solving [non]linear inclusions (and, in particular,…

Optimization and Control · Mathematics 2025-03-11 Quoc Tran-Dinh , Nghia Nguyen-Trung

In this paper, we consider the problem of solving a constrained system of nonlinear equations. We propose an algorithm based on a combination of the Newton and conditional gradient methods, and establish its local convergence analysis. Our…

Optimization and Control · Mathematics 2016-08-25 Max L. N. Goncalves , Jefferson G. Melo

We propose a new framework to design and analyze accelerated methods that solve general monotone equation (ME) problems $F(x)=0$. Traditional approaches include generalized steepest descent methods and inexact Newton-type methods. If $F$ is…

Optimization and Control · Mathematics 2024-07-22 Tianyi Lin , Michael. I. Jordan

We propose two basic assumptions, under which the rate of convergence of the augmented Lagrange method for a class of composite optimization problems is estimated. We analyze the rate of local convergence of the augmented Lagrangian method…

Optimization and Control · Mathematics 2017-09-05 Liwei Zhang , Yule Zhang , Jia Wu

Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages remains underexplored. Unlike prior studies requiring external schedulers and $\beta_2$ near…

Machine Learning · Computer Science 2026-05-26 Zhiwei Bai , Jiajie Zhao , Zhangchen Zhou , Zhi-Qin John Xu , Yaoyu Zhang

We present a novel approach to accelerate iterative methods to solve nonlinear Schr\"odinger eigenvalue problems using neural networks. Nonlinear eigenvector problems are fundamental in quantum mechanics and other fields, yet conventional…

Numerical Analysis · Mathematics 2025-07-23 Daniel Peterseim , Jan-F. Pietschmann , Jonas Püschel , Kilian Ruess

In this paper, we propose a third-order Newton's method which in each iteration solves a semidefinite program as a subproblem. Our approach is based on moving to the local minimum of the third-order Taylor expansion at each iteration,…

Optimization and Control · Mathematics 2023-06-08 Olha Silina , Jeffrey Zhang

This paper considers an enhancement of the classical iterated penalty Picard (IPP) method for the incompressible Navier-Stokes equations, where we restrict our attention to $O(1)$ penalty parameter, and Anderson acceleration (AA) is used to…

Numerical Analysis · Mathematics 2021-10-13 Leo G. Rebholz , Duygu Vargun , Mengying Xiao

The alternating direction method of multipliers (ADMM) has found widespread use in solving separable convex optimization problems. In this paper, by employing Nesterov extrapolation technique, we propose two families of accelerated…

Optimization and Control · Mathematics 2024-05-13 X. He , N. J. Huang , Y. P. Fang

The generalized alternating direction method of multipliers (ADMM) of Xiao et al. [{\tt Math. Prog. Comput., 2018}] aims at the two-block linearly constrained composite convex programming problem, in which each block is in the form of…

Optimization and Control · Mathematics 2022-04-05 Hongwu Li , Haibin Zhang , Yunhai Xiao

We present theoretical results on the convergence of \emph{non-convex} accelerated gradient descent in matrix factorization models with $\ell_2$-norm loss. The purpose of this work is to study the effects of acceleration in non-convex…

Machine Learning · Computer Science 2019-09-24 Tayo Ajayi , David Mildebrath , Anastasios Kyrillidis , Shashanka Ubaru , Georgios Kollias , Kristofer Bouchard