AI Chat AI Image Generator AI Video Text to Speech

Uniform Approximation by Neural Networks Activated by First and Second Order Ridge Splines

07/26/2016

∙

by Jason M. Klusowski, et al.

∙

∙

We establish sup-norm error bounds for functions that are approximated by linear combinations of first and second order ridge splines and show that these bounds are near-optimal.

Jason M. Klusowski
23 publications
Andrew R. Barron
5 publications

page 1

page 2

page 3

page 4

research

∙ 09/05/2023

A Unification Algorithm for Second-Order Linear Terms

We give an algorithm for the class of second order unification problems ...

0 Gilles Dowek, et al. ∙

research

∙ 04/04/2018

Identification of Shallow Neural Networks by Fewest Samples

We address the uniform approximation of sums of ridge functions ∑_i=1^m ...

0 Massimo Fornasier, et al. ∙

research

∙ 02/09/2017

Minimax Lower Bounds for Ridge Combinations Including Neural Nets

Estimation of functions of d variables is considered using ridge combi...

0 Jason M. Klusowski, et al. ∙

research

∙ 05/06/2019

Efficient Second-Order Shape-Constrained Function Fitting

We give an algorithm to compute a one-dimensional shape-constrained func...

0 David Durfee, et al. ∙

research

∙ 06/06/2023

Second order error bounds for POD-ROM methods based on first order divided differences

This note proves, for simplicity for the heat equation, that using BDF2 ...

0 Bosco García Archilla, et al. ∙

research

∙ 06/11/2018

The CCP Selector: Scalable Algorithms for Sparse Ridge Regression from Chance-Constrained Programming

Sparse regression and variable selection for large-scale data have been ...

0 Weijun Xie, et al. ∙

research

∙ 07/09/2021

Linear/Ridge expansions: Enhancing linear approximations by ridge functions

We consider approximations formed by the sum of a linear combination of ...

0 Constantin Greif, et al. ∙