English
Related papers

Related papers: An Augmented Lagrangian Method for Training Recurr…

200 papers

The un-rectifying technique expresses a non-linear point-wise activation function as a data-dependent variable, which means that the activation variable along with its input and output can all be employed in optimization. The ReLU network…

Machine Learning · Computer Science 2021-01-19 Wen-Liang Hwang , Shih-Shuo Tung

As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. Recently, it has attracted the attention of deep learning…

Machine Learning · Computer Science 2021-12-23 Junxiang Wang , Hongyi Li , Liang Zhao

In this article we study the stochastic gradient descent (SGD) optimization method in the training of fully-connected feedforward artificial neural networks with ReLU activation. The main result of this work proves that the risk of the SGD…

Numerical Analysis · Mathematics 2022-09-28 Arnulf Jentzen , Adrian Riekert

First-order methods have been studied for nonlinear constrained optimization within the framework of the augmented Lagrangian method (ALM) or penalty method. We propose an improved inexact ALM (iALM) and conduct a unified analysis for…

Optimization and Control · Mathematics 2021-03-25 Zichong Li , Pin-Yu Chen , Sijia Liu , Songtao Lu , Yangyang Xu

In this paper, we develop unrolled neural networks to solve constrained optimization problems, offering accelerated, learnable counterparts to dual ascent (DA) algorithms. Our framework, termed constrained dual unrolling (CDU), comprises…

Machine Learning · Computer Science 2026-01-27 Samar Hadou , Alejandro Ribeiro

Physics and equality constrained artificial neural networks (PECANN) are grounded in methods of constrained optimization to properly constrain the solution of partial differential equations (PDEs) with their boundary and initial conditions…

Machine Learning · Computer Science 2023-07-18 Shamsulhaq Basir , Inanc Senocak

This dissertation explores block decomposable methods for large-scale optimization problems. It focuses on alternating direction method of multipliers (ADMM) schemes and block coordinate descent (BCD) methods. Specifically, it introduces a…

Optimization and Control · Mathematics 2026-01-15 Leandro Farias Maia

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs…

Machine Learning · Computer Science 2018-05-23 Jinmian Ye , Linnan Wang , Guangxi Li , Di Chen , Shandian Zhe , Xinqi Chu , Zenglin Xu

This paper focuses on integrating the networks and adversarial training into constrained optimization problems to develop a framework algorithm for constrained optimization problems. For such problems, we first transform them into minimax…

Optimization and Control · Mathematics 2024-07-08 Gang Bao , Dong Wang , Boyi Zou

This paper presents a new deep learning-based framework for robust nonlinear estimation and control using the concept of a Neural Contraction Metric (NCM). The NCM uses a deep long short-term memory recurrent neural network for a global…

Systems and Control · Electrical Eng. & Systems 2020-11-20 Hiroyasu Tsukamoto , Soon-Jo Chung

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. Till this day in the scientific…

Machine Learning · Computer Science 2023-04-13 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg S. Weiss

We investigate the physics-constrained training of an encoder-decoder neural network for approximating the Fokker-Planck-Landau collision operator in the 5-dimensional kinetic fusion simulation in XGC. To train this network, we propose a…

Computational Physics · Physics 2020-09-17 Alp Dener , Marco Andres Miller , Randy Michael Churchill , Todd Munson , Choong-Seock Chang

We present a GPU implementation of Algorithm NCL, an augmented Lagrangian method for solving large-scale and degenerate nonlinear programs. Although interior-point methods and sequential quadratic programming are widely used for solving…

Optimization and Control · Mathematics 2025-10-08 Alexis Montoison , François Pacaud , Michael Saunders , Sungho Shin , Dominique Orban

Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. Fixed penalty methods, though common, lack adaptability and suffer from hyperparameter sensitivity. In this paper, we propose a…

Machine Learning · Computer Science 2023-10-26 Diogo Lavado , Cláudia Soares , Alessandra Micheletti

Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known…

Machine Learning · Computer Science 2016-02-25 Nitish Shirish Keskar , Albert S. Berahas

This paper investigates the use of extended Kalman filtering to train recurrent neural networks with rather general convex loss functions and regularization terms on the network parameters, including $\ell_1$-regularization. We show that…

Machine Learning · Computer Science 2022-11-03 Alberto Bemporad

In many numerical simulations stochastic gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) but till this day it remains an open problem of research to provide a…

Machine Learning · Computer Science 2023-06-26 Martin Hutzenthaler , Arnulf Jentzen , Katharina Pohl , Adrian Riekert , Luca Scarpa

Deep neural networks (DNNs) are notorious for making more mistakes for the classes that have substantially fewer samples than the others during training. Such class imbalance is ubiquitous in clinical applications and very crucial to handle…

Machine Learning · Computer Science 2022-01-06 Sara Sangalli , Ertunc Erdil , Andreas Hoetker , Olivio Donati , Ender Konukoglu

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of…

Machine Learning · Statistics 2018-03-28 Tim Tsz-Kit Lau , Jinshan Zeng , Baoyuan Wu , Yuan Yao

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient…

Machine Learning · Computer Science 2016-05-09 Gavin Taylor , Ryan Burmeister , Zheng Xu , Bharat Singh , Ankit Patel , Tom Goldstein