Regularisation in neural networks: a survey and empirical analysis of approaches

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Opperman, Christiaan P., Bosman, Anna S., Malan, Katherine M.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917235442843648
author Opperman, Christiaan P.
Bosman, Anna S.
Malan, Katherine M.
author_facet Opperman, Christiaan P.
Bosman, Anna S.
Malan, Katherine M.
contents Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks, collectively known as regularisation techniques. These are used as common practice under the assumption that any regularisation added to the pipeline would result in a performance improvement. In this study, we investigate whether this assumption holds in practice. First, we provide a broad review of regularisation techniques, including modern theories such as double descent. We propose a taxonomy of methods under four broad categories, namely: (1) data-based strategies, (2) architecture strategies, (3) training strategies, and (4) loss function strategies. Notably, we highlight the contradictions and correspondences between the approaches in these broad classes. Further, we perform an empirical comparison of the various regularisation techniques on classification tasks for ten numerical and image datasets applied to the multi-layer perceptron and convolutional neural network architectures. Results show that the efficacy of regularisation is dataset-dependent. For example, the use of a regularisation term only improved performance on numeric datasets, whereas batch normalisation improved performance on image datasets only. Generalisation is crucial to machine learning; thus, understanding the effects of applying regularisation techniques, and considering the connections between them is essential to the appropriate use of these methods in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23131
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Regularisation in neural networks: a survey and empirical analysis of approaches
Opperman, Christiaan P.
Bosman, Anna S.
Malan, Katherine M.
Machine Learning
Artificial Intelligence
I.2.6; I.5.1; I.5.2; I.5.3
Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks, collectively known as regularisation techniques. These are used as common practice under the assumption that any regularisation added to the pipeline would result in a performance improvement. In this study, we investigate whether this assumption holds in practice. First, we provide a broad review of regularisation techniques, including modern theories such as double descent. We propose a taxonomy of methods under four broad categories, namely: (1) data-based strategies, (2) architecture strategies, (3) training strategies, and (4) loss function strategies. Notably, we highlight the contradictions and correspondences between the approaches in these broad classes. Further, we perform an empirical comparison of the various regularisation techniques on classification tasks for ten numerical and image datasets applied to the multi-layer perceptron and convolutional neural network architectures. Results show that the efficacy of regularisation is dataset-dependent. For example, the use of a regularisation term only improved performance on numeric datasets, whereas batch normalisation improved performance on image datasets only. Generalisation is crucial to machine learning; thus, understanding the effects of applying regularisation techniques, and considering the connections between them is essential to the appropriate use of these methods in practice.
title Regularisation in neural networks: a survey and empirical analysis of approaches
topic Machine Learning
Artificial Intelligence
I.2.6; I.5.1; I.5.2; I.5.3
url https://arxiv.org/abs/2601.23131