Saved in:
Bibliographic Details
Main Authors: Zhao, Jim, Singh, Sidak Pal, Lucchi, Aurelien
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.02139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912249209159680
author Zhao, Jim
Singh, Sidak Pal
Lucchi, Aurelien
author_facet Zhao, Jim
Singh, Sidak Pal
Lucchi, Aurelien
contents The Gauss-Newton (GN) matrix plays an important role in machine learning, most evident in its use as a preconditioning matrix for a wide family of popular adaptive methods to speed up optimization. Besides, it can also provide key insights into the optimization landscape of neural networks. In the context of deep neural networks, understanding the GN matrix involves studying the interaction between different weight matrices as well as the dependencies introduced by the data, thus rendering its analysis challenging. In this work, we take a first step towards theoretically characterizing the conditioning of the GN matrix in neural networks. We establish tight bounds on the condition number of the GN in deep linear networks of arbitrary depth and width, which we also extend to two-layer ReLU networks. We expand the analysis to further architectural components, such as residual connections and convolutional layers. Finally, we empirically validate the bounds and uncover valuable insights into the influence of the analyzed architectural components.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02139
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks
Zhao, Jim
Singh, Sidak Pal
Lucchi, Aurelien
Machine Learning
The Gauss-Newton (GN) matrix plays an important role in machine learning, most evident in its use as a preconditioning matrix for a wide family of popular adaptive methods to speed up optimization. Besides, it can also provide key insights into the optimization landscape of neural networks. In the context of deep neural networks, understanding the GN matrix involves studying the interaction between different weight matrices as well as the dependencies introduced by the data, thus rendering its analysis challenging. In this work, we take a first step towards theoretically characterizing the conditioning of the GN matrix in neural networks. We establish tight bounds on the condition number of the GN in deep linear networks of arbitrary depth and width, which we also extend to two-layer ReLU networks. We expand the analysis to further architectural components, such as residual connections and convolutional layers. Finally, we empirically validate the bounds and uncover valuable insights into the influence of the analyzed architectural components.
title Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2411.02139