English
Related papers

Related papers: Convergence theory for Hermite approximations unde…

200 papers

Transformers are a type of neural network that have demonstrated remarkable performance across various domains, particularly in natural language processing tasks. Motivated by this success, research on the theoretical understanding of…

Machine Learning · Computer Science 2025-02-18 Naoki Takeshita , Masaaki Imaizumi

We present a constructive approximation framework for analyzing the expressive power of Fourier residual networks in approximating a broad class of one-dimensional functions. Our study covers both piecewise continuous functions -- including…

Numerical Analysis · Mathematics 2026-05-06 Owen Davis , Mohammad Motamed , Olof Runborg

Image restoration is an inherently ill posed inverse problem. Equivariant networks that embed geometric symmetry priors can mitigate this ill posedness and improve performance. However, current understanding of the relationship between…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Feiyu Tan , Qi Xie , Zongben Xu , Deyu Meng

A new method to represent and approximate rotation matrices is introduced. The method represents approximations of a rotation matrix $Q$ with linearithmic complexity, i.e. with $\frac{1}{2}n\lg(n)$ rotations over pairs of coordinates,…

Machine Learning · Computer Science 2014-04-30 Michael Mathieu , Yann LeCun

F. Stenger proposed efficient approximation formulas for derivatives over infinite intervals. These formulas were derived by combining the Sinc approximation with appropriate conformal maps. It has been demonstrated that these formulas can…

Numerical Analysis · Mathematics 2026-03-03 Tomoaki Okayama , Yuito Kuwashita , Ao Kondo

We derive an effective field theory (EFT) for cosmological Lyman alpha forest fluctuations valid for the power spectrum at the one-loop order. The ``bottom-up'' EFT expansion at the level of the transmitted flux is identical to the…

Cosmology and Nongalactic Astrophysics · Physics 2024-01-04 Mikhail M. Ivanov

In this paper, we propose a gradient boosting algorithm called \textit{adaptive boosting histogram transform} (\textit{ABHT}) for regression to illustrate the local adaptivity of gradient boosting algorithms in histogram transform ensemble…

Machine Learning · Statistics 2021-12-07 Hanyuan Hang

We consider a framework for the construction of iterative schemes for operator equations that combine low-rank approximation in tensor formats and adaptive approximation in a basis. Under fairly general assumptions, we obtain a rigorous…

Numerical Analysis · Mathematics 2014-03-17 Markus Bachmayr , Wolfgang Dahmen

The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference,…

Machine Learning · Statistics 2016-06-15 Danilo Jimenez Rezende , Shakir Mohamed

In this paper, we propose a new trigonometric interpolation algorithm and establish relevant convergent properties. The method adjusts an existing trigonometric interpolation algorithm such that it can better leverage Fast Fourier Transform…

Numerical Analysis · Mathematics 2025-05-06 Xiaorong Zou

The machine learning random Fourier feature method for data in high dimension is computationally and theoretically attractive since the optimization is based on a convex standard least squares problem and independent sampling of Fourier…

Numerical Analysis · Mathematics 2026-05-19 Xin Huang , Aku Kammonen , Anamika Pandey , Mattias Sandberg , Erik von Schwerin , Anders Szepessy , Raúl Tempone

Functions of one or more variables are usually approximated with a basis: a complete, linearly-independent system of functions that spans a suitable function space. The topic of this paper is the numerical approximation of functions using…

Numerical Analysis · Mathematics 2018-11-07 Ben Adcock , Daan Huybrechs

Motivated by a constrained minimization problem, it is studied the gradient flows with respect to Hessian Riemannian metrics induced by convex functions of Legendre type. The first result characterizes Hessian Riemannian structures on…

Optimization and Control · Mathematics 2018-11-27 Felipe Alvarez , Jérôme Bolte , Olivier Brahic

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

A systematic mismatch exists between mathematically ideal and effective activation updates during gradient descent. As intended, parameters update in their direction of steepest descent. However, activations are argued to constitute a more…

Machine Learning · Computer Science 2026-03-11 George Bird

The loss landscapes of deep neural networks are not well understood due to their high nonconvexity. Empirically, the local minima of these loss functions can be connected by a learned curve in model space, along which the loss remains…

Machine Learning · Computer Science 2020-12-11 N. Joseph Tatro , Pin-Yu Chen , Payel Das , Igor Melnyk , Prasanna Sattigeri , Rongjie Lai

Nonuniform Fourier data are routinely collected in applications such as magnetic resonance imaging, synthetic aperture radar, and synthetic imaging in radio astronomy. To acquire a fast reconstruction that does not require an online inverse…

Numerical Analysis · Mathematics 2016-10-05 Anne Gelb , Guohui Song

We consider applications of neural networks in nonlinear system identification and formulate a hypothesis that adjusting general network structure by incorporating frequency information or other known orthogonal transform, should result in…

Machine Learning · Computer Science 2025-01-24 Krzysztof Zając , Wojciech Sopot , Paweł Wachel

The FC-Gram trigonometric polynomial approximation of a non-periodic function that interpolates the function on equispaced grids was introduced in 2010 by Bruno and Lyon [J. Comput. Phys, 229(6):2009-2033, 2010]. Since then, the…

Numerical Analysis · Mathematics 2024-09-04 Akash Anand , Prakash Nainwal

In this paper, we propose a geometric framework to analyze the convergence properties of gradient descent trajectories in the context of linear neural networks. We translate a well-known empirical observation of linear neural nets into a…

Machine Learning · Computer Science 2023-08-02 Yacine Chitour , Zhenyu Liao , Romain Couillet