Approximation and interpolation of deep neural networks

Vlad-Raul Constantinescu, Ionel Popescu
4/20/2023
cs.LGmath.OCmath.PR

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

In this paper, we prove that in the overparametrized regime, deep neural network provide universal approximations and can interpolate any data set, as long as the activation function is locally in $L^1(\RR)$ and not an affine function. Additionally, if the activation function is smooth and such an interpolation networks exists, then the set of parameters which interpolate forms a manifold. Furthermore, we give a characterization of the Hessian of the loss function evaluated at the interpolation points. In the last section, we provide a practical probabilistic method of finding such a point under general conditions on the activation function.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Interpolation, Approximation and Controllability of Deep Neural Networks

85% match2023

Function Extrapolation with Neural Networks and Its Application for Manifolds

83% match1 repo22024

A new approach to generalisation error of machine learning algorithms: Estimates and convergence

83% match2023

Approximation of Nonlinear Functionals Using Deep ReLU Networks

82% match2023

Kernel interpolation generalizes poorly

81% match2023

Deep neural network approximation of composite functions without the curse of dimensionality

80% match2023

Cite this paper

@article{constantinescu2023approximation,
  title  = {Approximation and interpolation of deep neural networks},
  author = {Vlad-Raul Constantinescu and Ionel Popescu},
  year   = {2023},
  eprint = {2304.10552},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.10552v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.10552.svg)](https://codeofpaper.com/paper/2304.10552)

Discussion