Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Arnal, Charles, Berenfeld, Clement, Rosenberg, Simon, Cabannes, Vivien
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.01375
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929694610292736
author Arnal, Charles
Berenfeld, Clement
Rosenberg, Simon
Cabannes, Vivien
author_facet Arnal, Charles
Berenfeld, Clement
Rosenberg, Simon
Cabannes, Vivien
contents Statistical learning in high-dimensional spaces is challenging without a strong underlying data structure. Recent advances with foundational models suggest that text and image data contain such hidden structures, which help mitigate the curse of dimensionality. Inspired by results from nonparametric statistics, we hypothesize that this phenomenon can be partially explained in terms of decomposition of complex tasks into simpler subtasks. In this paper, we present a controlled experimental framework to test whether neural networks can indeed exploit such "hidden factorial structures". We find that they do leverage these latent patterns to learn discrete distributions more efficiently. We also study the interplay between our structural assumptions and the models' capacity for generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01375
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning with Hidden Factorial Structure
Arnal, Charles
Berenfeld, Clement
Rosenberg, Simon
Cabannes, Vivien
Machine Learning
Artificial Intelligence
Statistical learning in high-dimensional spaces is challenging without a strong underlying data structure. Recent advances with foundational models suggest that text and image data contain such hidden structures, which help mitigate the curse of dimensionality. Inspired by results from nonparametric statistics, we hypothesize that this phenomenon can be partially explained in terms of decomposition of complex tasks into simpler subtasks. In this paper, we present a controlled experimental framework to test whether neural networks can indeed exploit such "hidden factorial structures". We find that they do leverage these latent patterns to learn discrete distributions more efficiently. We also study the interplay between our structural assumptions and the models' capacity for generalization.
title Learning with Hidden Factorial Structure
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.01375