English
Related papers

Related papers: Estimating the Jacobian matrix of an unknown multi…

200 papers

In this paper, we study the Jacobi frame approximation with equispaced samples and derive an error estimation. We observe numerically that the approximation accuracy gradually decreases as the extended domain parameter $\gamma$ increases in…

Numerical Analysis · Mathematics 2022-02-23 Xianru Chen

Multivariate function approximation is a fundamental problem in machine learning. Classic multivariate function approximations rely on hand-crafted basis functions (e.g., polynomial basis and Fourier basis), which limits their approximation…

Machine Learning · Computer Science 2026-03-17 Wei-Hao Wu , Ting-Zhu Huang , Xi-Le Zhao , Yisi Luo , Deyu Meng

We propose a new loss function for supervised and physics-informed training of neural networks and operators that incorporates a posteriori error estimate. More specifically, during the training stage, the neural network learns additional…

Numerical Analysis · Mathematics 2024-02-09 Vladimir Fanaskov , Alexander Rudikov , Ivan Oseledets

A well-conditioned Jacobian spectrum has a vital role in preventing exploding or vanishing gradients and speeding up learning of deep neural networks. Free probability theory helps us to understand and handle the Jacobian spectrum. We…

Probability · Mathematics 2020-02-13 Tomohiro Hayase

Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capabilities of neural networks trained via gradient descent. We…

Machine Learning · Computer Science 2019-07-05 Samet Oymak , Zalan Fabian , Mingchen Li , Mahdi Soltanolkotabi

In appropriate frameworks, automatic differentiation is transparent to the user at the cost of being a significant computational burden when the number of operations is large. For iterative algorithms, implicit differentiation alleviates…

Optimization and Control · Mathematics 2023-05-24 Jérôme Bolte , Edouard Pauwels , Samuel Vaiter

By using the Hadamard matrix product concept, this paper introduces two generalized matrix formulation forms of numerical analogue of nonlinear differential operators. The SJT matrix-vector product approach is found to be a simple,…

Computational Engineering, Finance, and Science · Computer Science 2024-09-21 W. Chen

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…

Machine Learning · Computer Science 2019-05-30 Zhouyuan Huo , Bin Gu , Heng Huang

Neural stochastic differential equation model with a Brownian motion term can capture epistemic uncertainty of deep neural network from the perspective of a dynamical system. The goal of this paper is to improve the convergence rate of the…

Numerical Analysis · Mathematics 2025-09-09 Daili Sheng , Minghui Song , Xiang Peng , Xuanqi Dong

The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm. The main…

Systems and Control · Electrical Eng. & Systems 2025-06-06 Cesare Donati , Martina Mammarella , Fabrizio Dabbene , Carlo Novara , Constantino Lagoa

Recent large scale genome wide association analysis involves large scale linear mixed models. Quantifying (co)-variance parameters in the mixed models with a restricted maximum likelihood method results in a score function which is the…

Numerical Analysis · Mathematics 2016-08-26 Shengxin Zhu

Gradient descent during the learning process of a neural network can be subject to many instabilities. The spectral density of the Jacobian is a key component for analyzing stability. Following the works of Pennington et al., such Jacobians…

Machine Learning · Statistics 2023-04-26 Reda Chhaibi , Tariq Daouda , Ezechiel Kahn

Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abundant theoretical…

Machine Learning · Statistics 2024-12-18 Dongya Wu , Xin Li

This paper provides a general proof of a relationship theorem between nonlinear analogue polynomial equations and the corresponding Jacobian matrix, presented recently by the present author. This theorem is also verified generally effective…

Numerical Analysis · Mathematics 2025-10-20 W. Chen

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a…

Graphics · Computer Science 2022-05-09 Noam Aigerman , Kunal Gupta , Vladimir G. Kim , Siddhartha Chaudhuri , Jun Saito , Thibault Groueix

There is growing interest in learning Fourier domain sampling strategies (particularly for magnetic resonance imaging, MRI) using optimization approaches. For non-Cartesian sampling patterns, the system models typically involve non-uniform…

Image and Video Processing · Electrical Eng. & Systems 2023-02-07 Guanhua Wang , Jeffrey A. Fessler

Apart from solving complicated problems that require a certain level of intelligence, fine-tuned deep neural networks can also create fast algorithms for slow, numerical tasks. In this paper, we introduce an improved version of [1]'s work,…

Robotics · Computer Science 2018-09-17 Peiyuan Liao , Jiajun Mao

The Jacobian matrix of a dynamical system describes its response to perturbations. Conversely one can estimate the Jacobian matrix by carefully monitoring how the system responds to environmental noise. Here we present a closed form…

Chaotic Dynamics · Physics 2019-10-23 Edmund Barter , Andreas Brechtel , Barbara Drossel , Thilo Gross

Probabilistic modeling enables combining domain knowledge with learning from data, thereby supporting learning from fewer training instances than purely data-driven methods. However, learning probabilistic models is difficult and has not…

Machine Learning · Computer Science 2017-05-17 Avi Pfeffer

Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good…

Machine Learning · Statistics 2020-12-29 Simón Rodríguez Santana , Daniel Hernández-Lobato