Non-identifiability distinguishes Neural Networks among Parametric Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chatterjee, Sourav, Sudijono, Timothy
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915305889988608
author Chatterjee, Sourav
Sudijono, Timothy
author_facet Chatterjee, Sourav
Sudijono, Timothy
contents One of the enduring problems surrounding neural networks is to identify the factors that differentiate them from traditional statistical models. We prove a pair of results which distinguish feedforward neural networks among parametric models at the population level, for regression tasks. Firstly, we prove that for any pair of random variables $(X,Y)$, neural networks always learn a nontrivial relationship between $X$ and $Y$, if one exists. Secondly, we prove that for reasonable smooth parametric models, under local and global identifiability conditions, there exists a nontrivial $(X,Y)$ pair for which the parametric model learns the constant predictor $\mathbb{E}[Y]$. Together, our results suggest that a lack of identifiability distinguishes neural networks among the class of smooth parametric models.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18017
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Non-identifiability distinguishes Neural Networks among Parametric Models
Chatterjee, Sourav
Sudijono, Timothy
Statistics Theory
Machine Learning
One of the enduring problems surrounding neural networks is to identify the factors that differentiate them from traditional statistical models. We prove a pair of results which distinguish feedforward neural networks among parametric models at the population level, for regression tasks. Firstly, we prove that for any pair of random variables $(X,Y)$, neural networks always learn a nontrivial relationship between $X$ and $Y$, if one exists. Secondly, we prove that for reasonable smooth parametric models, under local and global identifiability conditions, there exists a nontrivial $(X,Y)$ pair for which the parametric model learns the constant predictor $\mathbb{E}[Y]$. Together, our results suggest that a lack of identifiability distinguishes neural networks among the class of smooth parametric models.
title Non-identifiability distinguishes Neural Networks among Parametric Models
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2504.18017