English
Related papers

Related papers: Improved architectures and training algorithms for…

200 papers

Thanks to their universal approximation properties and new efficient training strategies, Deep Neural Networks are becoming a valuable tool for the approximation of mathematical operators. In the present work, we introduce Mesh-Informed…

Numerical Analysis · Mathematics 2023-05-08 Nicola Rares Franco , Andrea Manzoni , Paolo Zunino

Operator learning aims to discover properties of an underlying dynamical system or partial differential equation (PDE) from data. Here, we present a step-by-step guide to operator learning. We explain the types of problems and PDEs amenable…

Numerical Analysis · Mathematics 2025-04-30 Nicolas Boullé , Alex Townsend

This focused review explores a range of neural operator architectures for approximating solutions to parametric partial differential equations (PDEs), emphasizing high-level concepts and practical implementation strategies. The study covers…

Computational Engineering, Finance, and Science · Computer Science 2025-03-10 Prashant K. Jha

Recent theoretical works based on the neural tangent kernel (NTK) have shed light on the optimization and generalization of over-parameterized networks, and partially bridge the gap between their practical success and classical learning…

Machine Learning · Computer Science 2020-08-10 Kyung-Su Kim , Aurélie C. Lozano , Eunho Yang

We present a novel framework combining Deep Operator Networks (DeepONets) with Physics-Informed Neural Networks (PINNs) to solve partial differential equations (PDEs) and estimate their unknown parameters. By integrating data-driven…

Machine Learning · Computer Science 2025-08-05 Amogh Raj , Carol Eunice Gudumotou , Sakol Bun , Keerthana Srinivasa , Arash Sarshar

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal initialization in linear networks has been well-proven.…

Machine Learning · Computer Science 2021-07-22 Wei Huang , Weitao Du , Richard Yi Da Xu

State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain…

Machine Learning · Statistics 2019-11-01 Alberto Bietti , Julien Mairal

We explore the link between deep ensembles and Gaussian processes (GPs) through the lens of the Neural Tangent Kernel (NTK): a recent development in understanding the training dynamics of wide neural networks (NNs). Previous work has shown…

Machine Learning · Statistics 2020-10-27 Bobby He , Balaji Lakshminarayanan , Yee Whye Teh

Operator learning has emerged as a promising paradigm for approximating solution operators of partial differential equations (PDEs). However, conventional approaches typically rely on pointwise function discretizations, which often suffer…

Numerical Analysis · Mathematics 2026-02-03 Chuqi Chen , Yang Xiang , Weihong Zhang

Solving high-dimensional partial differential equations (PDEs) is a major challenge in scientific computing. We develop a new numerical method for solving elliptic-type PDEs by adapting the Q-learning algorithm in reinforcement learning.…

Numerical Analysis · Mathematics 2023-06-27 Samuel N. Cohen , Deqing Jiang , Justin Sirignano

The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces. The purpose of this work is to generalize…

Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by…

Machine Learning · Computer Science 2023-05-29 Yuqing Li , Tao Luo , Nung Kwan Yip

Spectral methods are an important part of scientific computing's arsenal for solving partial differential equations (PDEs). However, their applicability and effectiveness depend crucially on the choice of basis functions used to expand the…

Numerical Analysis · Mathematics 2021-11-10 Brek Meuris , Saad Qadeer , Panos Stinis

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints.…

Machine Learning · Computer Science 2025-11-26 Shaharyar Ahmed Khan Tareen , Filza Khan Tareen

The Neural Tangent Kernel (NTK) viewpoint is widely employed to analyze the training dynamics of overparameterized Physics-Informed Neural Networks (PINNs). However, unlike the case of linear Partial Differential Equations (PDEs), we show…

Machine Learning · Computer Science 2024-11-01 Andrea Bonfanti , Giuseppe Bruno , Cristina Cipriani

Little is known about the training dynamics of equivariant neural networks, in particular how it compares to data augmented training of their non-equivariant counterparts. Recently, neural tangent kernels (NTKs) have emerged as a powerful…

Machine Learning · Computer Science 2025-02-03 Philipp Misof , Pan Kessel , Jan E. Gerken

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

Pretraining for partial differential equation (PDE) modeling has recently shown promise in scaling neural operators across datasets to improve generalizability and performance. Despite these advances, our understanding of how pretraining…

Machine Learning · Computer Science 2024-10-03 Anthony Zhou , Cooper Lorsung , AmirPouya Hemmasian , Amir Barati Farimani

A novel approach to approximate solutions of Stochastic Differential Equations (SDEs) by Deep Neural Networks is derived and analysed. The architecture is inspired by the notion of Deep Operator Networks (DeepONets), which is based on…

Numerical Analysis · Mathematics 2025-12-23 Martin Eigel , Charles Miranda
‹ Prev 1 3 4 5 6 7 10 Next ›