English
Related papers

Related papers: Learning Orthonormal Bases for Function Spaces

200 papers

An orthonormal basis matrix $X$ of a subspace ${\cal X}$ is known not to be unique, unless there are some kinds of normalization requirements. One of them is to require that $X^{\rm T}D$ is positive semi-definite, where $D$ is a constant…

Numerical Analysis · Mathematics 2023-04-04 Zhongming Teng , Ren-Cang Li

Continuous-time deep learning models, such as neural ordinary differential equations (ODEs), offer a promising framework for surrogate modeling of complex physical systems. A central challenge in training these models lies in learning…

Machine Learning · Computer Science 2025-07-30 Haley Rosso , Lars Ruthotto , Khachik Sargsyan

Incorporating neural networks for the solution of Ordinary Differential Equations (ODEs) represents a pivotal research direction within computational mathematics. Within neural network architectures, the integration of the intrinsic…

Dynamical Systems · Mathematics 2024-01-10 Shanshan Xiao , Jiawei Zhang , Yifa Tang

A set of exactly computable orthonormal basis functions that are useful in computations involving constituent quarks is presented. These basis functions are distinguished by the property that they fall off algebraically in momentum space…

Nuclear Theory · Physics 2009-10-30 B. D. Keister , W. N. Polyzou

We present a dimension-incremental method for function approximation in bounded orthonormal product bases to learn the solutions of various differential equations. Therefore, we decompose the source function of the differential equation…

Numerical Analysis · Mathematics 2025-05-20 Daniel Potts , Fabian Taubert

Computational optimal transport (OT) offers a principled framework for generative modeling. Neural OT methods, which use neural networks to learn an OT map (or potential) from data in an amortized way, can be evaluated out of sample after…

Machine Learning · Computer Science 2026-02-04 Alessandro Micheli , Yueqi Cao , Anthea Monod , Samir Bhatt

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

Neural networks are powerful function estimators, leading to their status as a paradigm of choice for modeling structured data. However, unlike other structured representations that emphasize the modularity of the problem -- e.g., factor…

Machine Learning · Computer Science 2022-06-20 Tsvetomila Mihaylova , Vlad Niculae , André F. T. Martins

Neural ordinary differential equations (NODE) have garnered significant attention for their design of continuous-depth neural networks and the ability to learn data/feature dynamics. However, for high-dimensional systems, estimating…

Machine Learning · Computer Science 2025-10-07 Muhao Guo , Haoran Li , Yang Weng

Crystallographic groups describe the symmetries of crystals and other repetitive structures encountered in nature and the sciences. These groups include the wallpaper and space groups. We derive linear and nonlinear representations of…

Machine Learning · Statistics 2023-06-09 Ryan P. Adams , Peter Orbanz

This work analyzes Graph Neural Networks, a generalization of Fully-Connected Deep Neural Nets on Graph structured data, when their width, that is the number of nodes in each fullyconnected layer is increasing to infinity. Infinite Width…

Machine Learning · Computer Science 2023-11-21 Yunus Cobanoglu

End-to-end representation learning has become a powerful tool for estimating causal quantities from high-dimensional observational data, but its efficiency remained unclear. Here, we face a central tension: End-to-end representation…

Machine Learning · Computer Science 2026-04-28 Valentyn Melnychuk , Dennis Frauen , Jonas Schweisthal , Stefan Feuerriegel

Modeling complex systems using standard neural ordinary differential equations (NODEs) often faces some essential challenges, including high computational costs and susceptibility to local optima. To address these challenges, we propose a…

Machine Learning · Computer Science 2024-05-24 Xin Li , Jingdong Zhang , Qunxi Zhu , Chengli Zhao , Xue Zhang , Xiaojun Duan , Wei Lin

We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces. The proposed approach is motivated by the recent successes of neural networks and deep learning, in combination with…

Numerical Analysis · Mathematics 2021-06-21 Kaushik Bhattacharya , Bamdad Hosseini , Nikola B. Kovachki , Andrew M. Stuart

We present a dimension-incremental algorithm for the nonlinear approximation of high-dimensional functions in an arbitrary bounded orthonormal product basis. Our goal is to detect a suitable truncation of the basis expansion of the…

Numerical Analysis · Mathematics 2023-04-28 Lutz Kämmerer , Daniel Potts , Fabian Taubert

Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In this paper, we generalize such square orthogonal matrix to…

Machine Learning · Computer Science 2017-11-22 Lei Huang , Xianglong Liu , Bo Lang , Adams Wei Yu , Yongliang Wang , Bo Li

Across scientific domains, a fundamental challenge is to characterize and compute the mappings from underlying physical processes to observed signals and measurements. While nonlinear neural networks have achieved considerable success, they…

Machine Learning · Computer Science 2025-08-11 Alexander DeLise , Kyle Loh , Krish Patel , Meredith Teague , Andrea Arnold , Matthias Chung

Despite their widespread success, the application of deep neural networks to functional data remains scarce today. The infinite dimensionality of functional data means standard learning algorithms can be applied only after appropriate…

Machine Learning · Statistics 2021-06-22 Junwen Yao , Jonas Mueller , Jane-Ling Wang

It has been known for a long time that initializing weight matrices to be orthogonal instead of having i.i.d. Gaussian components can improve training performance. This phenomenon can be analyzed using finite-width corrections, where the…

Machine Learning · Computer Science 2026-05-15 Max Guillen , Jan E. Gerken

Recently, orthogonal recurrent neural networks (RNNs) have emerged as state-of-the-art models for learning long-term dependencies. This class of models mitigates the exploding and vanishing gradients problem by design. In this work, we…

Machine Learning · Computer Science 2021-02-22 Omri Azencot , N. Benjamin Erichson , Mirela Ben-Chen , Michael W. Mahoney