English
Related papers

Related papers: Schauder Bases for $C[0, 1]$ Using ReLU, Softplus …

200 papers

The closed span of Rademacher functions is investigated in the weighted spaces X(w), where X is a symmetric space on [0,1] and w is a positive measurable function on [0,1]. By using the notion and properties of the Rademacher multiplicator…

Functional Analysis · Mathematics 2015-08-07 Sergey Astashkin

We discuss the expressive power of neural networks which use the non-smooth ReLU activation function $\varrho(x) = \max\{0,x\}$ by analyzing the approximation theoretic properties of such networks. The existing results mainly fall into two…

Functional Analysis · Mathematics 2019-04-10 Felix Voigtlaender , Philipp Petersen

We present two new classes of orthogonal functions, log orthogonal functions (LOFs) and generalized log orthogonal functions (GLOFs), which are constructed by applying a $\log$ mapping to Laguerre polynomials. We develop basic approximation…

Numerical Analysis · Mathematics 2020-03-04 Sheng Chen , Jie Shen

Activation functions play a pivotal role in the function learning using neural networks. The non-linearity in the learned function is achieved by repeated use of the activation function. Over the years, numerous activation functions have…

Machine Learning · Computer Science 2020-10-13 Koushik Biswas , Sandeep Kumar , Shilpak Banerjee , Ashish Kumar Pandey

We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small…

Machine Learning · Computer Science 2026-02-10 Abhigyan Dutta , Itay Safran , Paul Valiant

We prove existence of global minima in the loss landscape for the approximation of continuous target functions using shallow feedforward artificial neural networks with ReLU activation. This property is one of the fundamental artifacts…

Machine Learning · Computer Science 2024-11-20 Steffen Dereich , Sebastian Kassing

The aim of this note is to introduce a compound basis for the space of symmetric functions. Our basis consists of products of Schur functions and $Q$-functions. The basis elements are indexed by the partitions. It is well known that the…

Representation Theory · Mathematics 2007-05-23 Kazuya Aokage , Hiroshi Mizukawa , Hiro-Fumi Yamada

M\"untz spaces satisfying the M\"untz and gap conditions are considered. A Fourier approximation of functions in the M\"untz spaces $M_{\Lambda ,p}$ of $L_p$ functions is studied, where $1<p<\infty $. It is proved that up to an isomorphism…

Functional Analysis · Mathematics 2018-12-18 Sergey V. Ludkowski

We consider a filtration of the symmetric function space given by $\Lambda^{(k)}_t$, the linear span of Hall-Littlewood polynomials indexed by partitions whose first part is not larger than $k$. We introduce symmetric functions called the…

Combinatorics · Mathematics 2007-05-23 L. Lapointe , J. Morse

We show that the space $\mathcal{H}(\Omega)$ of holomorphic functions $F:\Omega\to\mathbb{C}$, where ${\Omega=\{(z,w)\in\widehat{\mathbb{C}}^2\,:\, z\cdot w\neq 1\}}$, possesses an orthogonal Schauder basis consisting of distinguished…

Complex Variables · Mathematics 2023-12-25 Annika Moucha

This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural…

Machine Learning · Computer Science 2019-05-08 I. Daubechies , R. DeVore , S. Foucart , B. Hanin , G. Petrova

We discuss constraints imposed by soft limits for effective field theories arising from symmetry breaking. In particular, we consider those associated with anomalous conformal symmetry as well as duality symmetries in supergravity. We…

High Energy Physics - Theory · Physics 2016-01-27 Yu-tin Huang , Congkao Wen

We obtain Schauder estimates for a class of concave fully nonlinear nonlocal parabolic equations of order $\sigma\in (0,2)$ with rough and non-symmetric kernels. As a application, we prove that the solution to a translation invariant…

Analysis of PDEs · Mathematics 2017-04-07 Hongjie Dong , Hong Zhang

In this paper, we investigate the application of radial basis functions (RBFs) for the approximation with collocation of the Stokes problem. The approximate solution is constructed in a multi-level fashion, each level using compactly…

Numerical Analysis · Mathematics 2014-09-29 Andrew Chernih , Quoc Thong Le Gia

This work focuses on the analysis of fully connected feed forward ReLU neural networks as they approximate a given, smooth function. In contrast to conventionally studied universal approximation properties under increasing architectures,…

Machine Learning · Computer Science 2024-06-24 Erion Morina , Martin Holler

We derive upper bounds on the difference between the orthogonal projections of a smooth function $u$ onto two finite element spaces that are nearby, in the sense that the support of every shape function belonging to one but not both of the…

Numerical Analysis · Mathematics 2014-08-19 Evan S. Gawlik , Adrian J. Lew

In the present investigation, we consider two new subclasses N_{{\Sigma}}^{{\mu}}({\alpha},{\lambda}) and N_{{\Sigma}}^{{\mu}}({\beta},{\lambda}) of bi-univalent functions defined in the open unit disk U={z:|z|<1}. Besides, we find upper…

Complex Variables · Mathematics 2012-04-20 Murat Çağlar , Halit Orhan , Nihat Yağmur

We study the asymptotics of Schur polynomials with partitions $\lambda$ which are almost staircase; more precisely, partitions that differ from $((m-1)(N-1),(m-1)(N-2),\ldots,(m-1),0)$ by at most one component at the beginning as…

Probability · Mathematics 2020-09-01 Zhongyang Li

Radial basis functions (RBFs) are prominent examples for reproducing kernels with associated reproducing kernel Hilbert spaces (RKHSs). The convergence theory for the kernel-based interpolation in that space is well understood and optimal…

Classical Analysis and ODEs · Mathematics 2023-09-15 Thomas Hangelbroek , Christian Rieger

In this paper, we propose compactly supported radial basis functions for solving some well- known classes of astrophysics problems categorized as non-linear singular initial ordinary dif- ferential equations on a semi-infinite domain. To…

Numerical Analysis · Mathematics 2016-05-31 Kourosh Parand , Mohammad Hemami