Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Constantinescu, Vlad-Raul, Popescu, Ionel
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2304.10552
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911851921539072
author Constantinescu, Vlad-Raul
Popescu, Ionel
author_facet Constantinescu, Vlad-Raul
Popescu, Ionel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_10552
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Approximation and interpolation of deep neural networks
Constantinescu, Vlad-Raul
Popescu, Ionel
Machine Learning
Optimization and Control
Probability
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.
title Approximation and interpolation of deep neural networks
topic Machine Learning
Optimization and Control
Probability
url https://arxiv.org/abs/2304.10552