From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bouniot, Quentin, Redko, Ievgen, Mallasto, Anton, Laclau, Charlotte, Struckmeier, Oliver, Arndt, Karol, Heinonen, Markus, Kyrki, Ville, Kaski, Samuel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916827242692608
author Bouniot, Quentin
Redko, Ievgen
Mallasto, Anton
Laclau, Charlotte
Struckmeier, Oliver
Arndt, Karol
Heinonen, Markus
Kyrki, Ville
Kaski, Samuel
author_facet Bouniot, Quentin
Redko, Ievgen
Mallasto, Anton
Laclau, Charlotte
Struckmeier, Oliver
Arndt, Karol
Heinonen, Markus
Kyrki, Ville
Kaski, Samuel
contents In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explaining the upward trend of their performance, however, remains difficult as different DNN architectures of comparable depth and width -- common factors associated with their expressive power -- may exhibit a drastically different performance even when trained on the same dataset. In this paper, we introduce the concept of the non-linearity signature of DNN, the first theoretically sound solution for approximately measuring the non-linearity of deep neural networks. Built upon a score derived from closed-form optimal transport mappings, this signature provides a better understanding of the inner workings of a wide range of DNN architectures and learning paradigms, with a particular emphasis on the computer vision task. We provide extensive experimental results that highlight the practical usefulness of the proposed non-linearity signature and its potential for long-reaching implications. The code for our work is available at https://github.com/qbouniot/AffScoreDeep
format Preprint
id arxiv_https___arxiv_org_abs_2310_11439
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Bouniot, Quentin
Redko, Ievgen
Mallasto, Anton
Laclau, Charlotte
Struckmeier, Oliver
Arndt, Karol
Heinonen, Markus
Kyrki, Ville
Kaski, Samuel
Machine Learning
Artificial Intelligence
In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explaining the upward trend of their performance, however, remains difficult as different DNN architectures of comparable depth and width -- common factors associated with their expressive power -- may exhibit a drastically different performance even when trained on the same dataset. In this paper, we introduce the concept of the non-linearity signature of DNN, the first theoretically sound solution for approximately measuring the non-linearity of deep neural networks. Built upon a score derived from closed-form optimal transport mappings, this signature provides a better understanding of the inner workings of a wide range of DNN architectures and learning paradigms, with a particular emphasis on the computer vision task. We provide extensive experimental results that highlight the practical usefulness of the proposed non-linearity signature and its potential for long-reaching implications. The code for our work is available at https://github.com/qbouniot/AffScoreDeep
title From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.11439