English
Related papers

Related papers: Learning via nonlinear conjugate gradients and dep…

200 papers

Learned iterative reconstruction algorithms for inverse problems offer the flexibility to combine analytical knowledge about the problem with modules learned from data. This way, they achieve high reconstruction performance while ensuring…

Image and Video Processing · Electrical Eng. & Systems 2022-10-24 Mareike Thies , Fabian Wagner , Mingxuan Gu , Lukas Folle , Lina Felsner , Andreas Maier

Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential…

Machine Learning · Computer Science 2019-08-28 Anil Kag , Ziming Zhang , Venkatesh Saligrama

This paper proposes the use of spectral element methods \citep{canuto_spectral_1988} for fast and accurate training of Neural Ordinary Differential Equations (ODE-Nets; \citealp{Chen2018NeuralOD}) for system identification. This is achieved…

Neural and Evolutionary Computing · Computer Science 2020-01-20 Alessio Quaglino , Marco Gallieri , Jonathan Masci , Jan Koutník

We study the problem of graph structure identification, i.e., of recovering the graph of dependencies among time series. We model these time series data as components of the state of linear stochastic networked dynamical systems. We assume…

Machine Learning · Computer Science 2023-06-29 Sérgio Machado , Anirudh Sridhar , Paulo Gil , Jorge Henriques , José M. F. Moura , Augusto Santos

Projection-based model reduction has become a popular approach to reduce the cost associated with integrating large-scale dynamical systems so they can be used in many-query settings such as optimization and uncertainty quantification. For…

Numerical Analysis · Mathematics 2020-08-26 Han Gao , Jian-Xun Wang , Matthew J. Zahr

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with…

Machine Learning · Computer Science 2024-12-17 Naoki Sato , Koshiro Izumi , Hideaki Iiduka

Gradient descent typically converges to a single minimum of the training loss without mechanisms to explore alternative minima that may generalize better. Searching for diverse minima directly in high-dimensional parameter space is…

Machine Learning · Computer Science 2025-09-16 Akshay Vegesna , Samip Dahal

This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular…

Machine Learning · Computer Science 2024-03-11 Changwoo Lee , Hun-Seok Kim

The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for…

Machine Learning · Computer Science 2023-05-29 Zefan Li , Bingbing Ni , Teng Li , WenJun Zhang , Wen Gao

Accurately learning solution operators for time-dependent partial differential equations (PDEs) from sparse and irregular data remains a challenging task. Recurrent DeepONet extensions inherit the discrete-time limitations of…

Computational Engineering, Finance, and Science · Computer Science 2025-07-04 Diab W. Abueidda , Mbebo Nonna , Panos Pantidis , Mostafa E. Mobasher

Residual networks (ResNets) are a deep learning architecture that substantially improved the state of the art performance in certain supervised learning tasks. Since then, they have received continuously growing attention. ResNets have a…

Machine Learning · Computer Science 2020-03-02 Johannes Müller

Recently, neural networks have been widely applied for solving partial differential equations (PDEs). Although such methods have been proven remarkably successful on practical engineering problems, they have not been shown, theoretically or…

Numerical Analysis · Mathematics 2023-03-27 Jonathan W. Siegel , Qingguo Hong , Xianlin Jin , Wenrui Hao , Jinchao Xu

In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of…

Systems and Control · Electrical Eng. & Systems 2023-09-18 Daniele Martinelli , Clara Lucía Galimberti , Ian R. Manchester , Luca Furieri , Giancarlo Ferrari-Trecate

Neural ordinary differential equations (neural ODEs) can effectively learn dynamical systems from time series data, but their behavior on graph-structured data remains poorly understood, especially when applied to graphs with different size…

Physics and Society · Physics 2026-02-10 Moritz Laber , Tina Eliassi-Rad , Brennan Klein

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

This paper presents a general description of a parameter estimation inverse problem for systems governed by nonlinear differential equations. The inverse problem is presented using optimal control tools with state constraints, where the…

Numerical Analysis · Mathematics 2018-06-28 Mohamed Kamel Riahi , Issam Al Qattan

The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the…

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar

Despite much research, Graph Neural Networks (GNNs) still do not display the favorable scaling properties of other deep neural networks such as Convolutional Neural Networks and Transformers. Previous work has identified issues such as…

Machine Learning · Computer Science 2023-12-19 Ameen Ali , Hakan Cevikalp , Lior Wolf

The deep operator network (DeepONet) is a popular neural operator architecture that has shown promise in solving partial differential equations (PDEs) by using deep neural networks to map between infinite-dimensional function spaces. In the…

Machine Learning · Computer Science 2025-02-25 Luis Mandl , Somdatta Goswami , Lena Lambers , Tim Ricken